CN113506229B - Neural network training and image generating method and device - Google Patents
Neural network training and image generating method and device Download PDFInfo
- Publication number
- CN113506229B CN113506229B CN202110799904.5A CN202110799904A CN113506229B CN 113506229 B CN113506229 B CN 113506229B CN 202110799904 A CN202110799904 A CN 202110799904A CN 113506229 B CN113506229 B CN 113506229B
- Authority
- CN
- China
- Prior art keywords
- reconstruction
- network
- loss
- color image
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 36
- 230000000007 visual effect Effects 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 60
- 238000003860 storage Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000000306 recurrent effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 17
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 6
- 238000013459 approach Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000003491 array Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004540 process dynamic Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Abstract
The disclosure relates to a neural network training and image generating method and device, wherein the method comprises the following steps: inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing to obtain a first reconstruction result; inputting a sample color image of the sample scene into a second reconstruction network for processing to obtain a second reconstruction result; determining the comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result; the first and second rebuilt networks are trained based on the integrated network loss. According to the neural network training method disclosed by the embodiment of the disclosure, the feature map corresponding to the dynamic visual information and the feature map corresponding to the color image can be more similar through training, the second reconstructed image output by the second reconstructed network can be more similar to the real color image, and the accuracy and the fidelity of the first reconstructed image which is similar to the second reconstructed image can be improved.
Description
Technical Field
The disclosure relates to the field of computer technology, and in particular, to a neural network training and image generating method and device.
Background
In the related art, the frame rate of the image or video frame collected by the camera or the camera is not high, the number of the video frames collected in a certain period of time is limited, if the speed of the photographed target object is fast, in the time interval between two video frames, it is difficult to photograph the target object, and it is also difficult to determine the pose of the target object, resulting in missing the action or track of the target object.
Disclosure of Invention
The disclosure provides a neural network training and image generating method and device.
According to an aspect of the present disclosure, there is provided an image neural network training method including: inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing to obtain a first reconstruction result, wherein the first reconstruction result comprises a multi-stage first feature map and a first reconstruction image; inputting a sample color image of the sample scene into a second reconstruction network for processing to obtain a second reconstruction result, wherein the second reconstruction result comprises a multi-stage second feature image and a second reconstruction image, and the sample color image is the same as the acquisition time of the sample dynamic visual information; determining a comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result; and training the first reconstruction network and the second reconstruction network according to the comprehensive network loss, wherein the first reconstruction network is used for generating a color image according to dynamic visual information, and the second reconstruction network is used for training the first reconstruction network.
In one possible implementation, determining a combined network loss of the first reconstruction network and the second reconstruction network from the sample color image, the first reconstruction result, and the second reconstruction result includes: determining a first network loss according to the first reconstruction result and the second reconstruction result; determining a second network loss from the second reconstructed image and the sample color image; and determining the comprehensive network loss according to the first network loss and the second network loss.
In one possible implementation, determining the first network loss according to the first reconstruction result and the second reconstruction result includes: determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map; determining a second sub-loss from the first reconstructed image and the second reconstructed image; and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
In one possible implementation, determining the integrated network loss from the first network loss and the second network loss includes: and carrying out weighted summation processing on the first network loss and the second network loss to obtain the comprehensive network loss.
In one possible implementation, the first reconstruction network includes a recurrent neural network and the second reconstruction network includes a convolutional neural network.
According to an aspect of the present disclosure, there is provided an image generating method including: and inputting the dynamic visual information of the preset scene acquired at a plurality of moments in the first time period into a first reconstruction network trained by the neural network training method for processing, and generating a first color image corresponding to each dynamic visual information.
In one possible implementation, the method further includes: and obtaining a video in the first time period of the preset scene according to the first color image and the second color image of the preset scene obtained in the first time period, wherein the obtaining frequency of the dynamic visual information is higher than that of the color image.
According to an aspect of the present disclosure, there is provided a neural network training device including: the first reconstruction module is used for inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing to obtain a first reconstruction result, wherein the first reconstruction result comprises a multi-stage first feature map and a first reconstruction image; the second reconstruction module is used for inputting a sample color image of the sample scene into a second reconstruction network for processing to obtain a second reconstruction result, wherein the second reconstruction result comprises a multi-stage second feature map and a second reconstruction image, and the sample color image is identical to the acquisition time of the sample dynamic visual information; the loss determination module is used for determining the comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result; the training module is used for training the first reconstruction network and the second reconstruction network according to the comprehensive network loss, wherein the first reconstruction network is used for generating color images according to dynamic visual information, and the second reconstruction network is used for training the first reconstruction network.
In one possible implementation, the loss determination module is further configured to: determining a first network loss according to the first reconstruction result and the second reconstruction result; determining a second network loss from the second reconstructed image and the sample color image; and determining the comprehensive network loss according to the first network loss and the second network loss.
In one possible implementation, the loss determination module is further configured to: determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map; determining a second sub-loss from the first reconstructed image and the second reconstructed image; and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
In one possible implementation, the first network loss and the second network loss are weighted and summed to obtain the integrated network loss.
In one possible implementation, the first reconstruction network includes a recurrent neural network and the second reconstruction network includes a convolutional neural network.
According to an aspect of the present disclosure, there is provided an image generating apparatus including: the generation module is used for inputting the dynamic visual information of the preset scene acquired at a plurality of moments in the first time period into the first reconstruction network trained by the neural network training device for processing, and generating a first color image corresponding to each dynamic visual information.
In one possible implementation, the apparatus further includes: the video generation module is used for obtaining videos in the first time period of the preset scene according to the first color image and the second color image of the preset scene obtained in the first time period, wherein the obtaining frequency of the dynamic visual information is higher than that of the color image.
According to an aspect of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.
According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.
FIG. 1 illustrates a flow chart of a neural network training method, according to an embodiment of the present disclosure;
FIG. 2 illustrates an application schematic of a neural network training method according to an embodiment of the present disclosure;
FIG. 3 illustrates a block diagram of a neural network training device, according to an embodiment of the present disclosure;
FIG. 4 shows a block diagram of an electronic device according to an embodiment of the disclosure;
fig. 5 shows a block diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Furthermore, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Fig. 1 shows a flowchart of a neural network training method according to an embodiment of the present disclosure, as shown in fig. 1, including:
In step S11, inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing, so as to obtain a first reconstruction result, wherein the first reconstruction result comprises a multi-stage first feature map and a first reconstruction image;
in step S12, inputting a sample color image of the sample scene into a second reconstruction network for processing, so as to obtain a second reconstruction result, where the second reconstruction result includes a multi-stage second feature map and a second reconstruction image, and the sample color image is the same as the acquisition time of the sample dynamic visual information;
in step S13, determining a comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result;
in step S14, training the first and second rebuilt networks based on the integrated network loss,
the first reconstruction network is used for generating color images according to dynamic visual information, and the second reconstruction network is used for training the first reconstruction network.
According to the neural network training method disclosed by the embodiment of the disclosure, through training, the first reconstruction result of the sample dynamic visual information obtained by the first reconstruction network is close to the second reconstruction result of the color image obtained by the second reconstruction network, and the first reconstruction network can obtain the color image with higher reality degree based on the sample dynamic visual information. Because the frequency of the dynamic visual information is higher than the acquisition frequency of the color image, the dynamic visual information is processed through the first reconstruction network, so that the acquisition frequency of the color image can be improved, the tracking of the motion trail or action of the moving object is facilitated, and the tracking effect is improved.
In one possible implementation, the neural network training method may be performed by an electronic device such as a terminal device or a server, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc., and the method may be implemented by a processor invoking computer readable instructions stored in a memory. Alternatively, the method may be performed by a server.
In one possible implementation, the dynamic vision receptors (Dynamic visual receptors, DVS) are sensitive to the rate of change of light intensity, and each pixel can record the amount of change in light intensity at that pixel location, and when the amount of change exceeds a threshold, a positive or negative pulse, i.e., dynamic visual information, is generated.
For example, an Event Camera (Event Camera) is a dynamic vision receptor that can be used to obtain the rate of change of light intensity of a preset scene. When a target in a preset scene is abnormal or performs certain actions, the light intensity of the target in the event camera can change to a certain extent, and the event camera can acutely capture the change to obtain dynamic visual information.
In one possible implementation, the frame rate of the dynamic vision receptor is higher than that of a normal camera or webcam, e.g., the frame rate of a camera or a conventional webcam is about 100fps, while the frame rate of the dynamic vision receptor is about 1,000,000fps. Therefore, in the time interval between the photographing of two frames of images by a common camera or a video camera, multiple frames of dynamic visual information can be photographed.
In one possible implementation, since the frequency of acquisition of color images is low, it is difficult to capture color images of a target object in the time interval between acquisition of two frames of color images, and the target object is also tracked by the color images. And the acquisition frequency of the dynamic visual information is high, a plurality of dynamic visual information can be acquired in the time interval between the acquisition of two frames of color images, and therefore, more color images can be acquired based on the dynamic visual information, for example, in the time interval between the acquisition of two frames of color images, color images are generated by the dynamic visual information for tracking the target object in the time interval.
In one possible implementation, the dynamic visual information is acquired at a high frequency, but the amount of information in the dynamic visual information of a single frame is small, and the pixel data is sparse. Feature extraction of dynamic visual information is difficult to obtain feature images rich in information, and color images are difficult to reconstruct based on the feature images.
In one possible implementation, based on the above-described problem, the dynamic visual information may be processed through a first reconstruction network for processing the dynamic visual information to generate a feature map from the dynamic visual information. The first reconstruction network may be trained prior to processing using the first reconstruction network. For example, training of the first reconstruction network may be aided by a second reconstruction network for processing color images. In an example, the first reconstruction result obtained by processing the dynamic visual information by the first reconstruction network may be approximated to the second reconstruction result obtained by processing the color image by the second reconstruction network, that is, the feature map obtained by processing the dynamic visual information by the first reconstruction network and the generated color image are respectively approximated to the feature map and the color image obtained by processing the color image by the second reconstruction network, so that the first reconstruction network can generate an image approximated to the real color image. In an example, the first reconstruction network includes a recurrent neural network and the second reconstruction network includes a convolutional neural network. The present disclosure does not limit the types of the first and second reestablished networks.
In one possible implementation, training may be performed with sample dynamic visual information and sample color images of the same scene. Multiple sample color images and sample dynamic visual information can be acquired for the same sample scene at the same time, and training can be performed by using the sample color images and the sample dynamic visual information which are acquired at the same time.
In a possible implementation manner, in step S11, the first reconstruction network may include an encoding sub-network and a decoding sub-network, the encoding sub-network may include a plurality of network levels, and may be used to obtain feature information of dynamic visual information, and the decoding sub-network may include a plurality of network levels, and may be used to decode based on the feature information, to obtain a first reconstruction result, that is, obtain a multi-level first feature map (i.e., a feature map output by each level of the decoding sub-network) and a first reconstructed image.
In a possible implementation manner, in step S12, the second reconstruction network may also include an encoding sub-network and a decoding sub-network, where the encoding sub-network may include a plurality of network levels and may be used to obtain feature information of the color image, and the decoding sub-network may include a plurality of network levels and may be used to decode based on the feature information, so as to obtain a second reconstruction result, that is, obtain a multi-level second feature map (i.e., a feature map output by each level of the decoding sub-network) and a second reconstructed image.
In one possible implementation, the purpose of this training is to enable the first reconstruction network to generate an image consistent with the color image based on the dynamic visual information, and thus, the first reconstruction image generated by the first reconstruction result may be more realistic and accurate by reducing the difference between the first reconstruction result of the first reconstruction network and the second reconstruction result of the second reconstruction network, and reducing the difference between the second reconstruction image and the color image. That is, the difference between each level of the first feature map in the first reconstruction result and the second feature map of the corresponding level in the second reconstruction result is reduced, and the difference between the first reconstruction image and the second reconstruction image is reduced, and the difference between the second reconstruction image and the color image is reduced. In this way, the accuracy of the feature map output by each level of the first reconstruction network can be improved, so that the fidelity and accuracy of the image generated by the first reconstruction network are further improved.
In one possible implementation, prior to training, errors may exist in both the first and second reconstruction networks, i.e., the first reconstruction result output by the first reconstruction network and the second reconstruction result output by the second reconstruction network are inconsistent, and/or the second reconstruction image output by the second reconstruction network is inconsistent with the sample color image.
In one possible implementation, in step S13, a combined network loss of the first reconstruction network and the second reconstruction network may be determined based on the sample color image, the first reconstruction result, and the second reconstruction result. As described above, there may be a difference between the first reconstruction result and the second reconstruction result, and there may be a difference between the second reconstruction image and the sample color image, and the network loss may be determined based on the difference, and the network loss may be gradually reduced through training to reduce the difference, so as to achieve the training purpose.
In one possible implementation, step S13 may include: determining a first network loss according to the first reconstruction result and the second reconstruction result; determining a second network loss from the second reconstructed image and the sample color image; and determining the comprehensive network loss according to the first network loss and the second network loss.
In one possible implementation, the first network loss may be determined according to the first reconstruction result and the second reconstruction result, and reducing the first network loss during the training may reduce a difference between the first reconstruction result and the second reconstruction result. The first reconstruction result and the second reconstruction result may each include a multi-level feature map and a reconstructed image, and differences between feature maps and differences between reconstructed images of corresponding levels may be determined, respectively, to thereby determine the first network loss.
In one possible implementation, determining the first network loss according to the first reconstruction result and the second reconstruction result includes: determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map; determining a second sub-loss from the first reconstructed image and the second reconstructed image; and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
In one possible implementation, the first reconstruction result may include an n-level feature map, the second reconstruction result may include an m-level feature map, m and n are positive integers, and m and n may be equal or unequal. The feature map with the same resolution (i.e., feature map with the same scale) may be selected from the first reconstruction result and the second reconstruction result, and the sub-loss of each stage may be determined based on the feature map with the same resolution, for example, the resolution of the 1 st first feature map in the first reconstruction result and the resolution of the 2 nd second feature map in the second reconstruction result are equal, and the resolution of the 2 nd first feature map in the first intermediate result and the resolution of the 4 nd second feature map in the second reconstruction result are equal, and the first sub-loss may be determined based on the 1 st first feature map in the first reconstruction result and the 2 nd second feature map in the second reconstruction result.
In an example, the first reconstruction result includes the same number of levels of the first feature map as the second reconstruction result includes the same number of levels of the second feature map, and the resolutions of the first feature map and the second feature map at the respective levels are also the same. For example, the number of network levels of the decoding subnetwork of the first reconstruction network is equal to the number of network levels of the decoding subnetwork of the second reconstruction network, and the upsampling rates of the network levels are equal. In this case, the first sub-loss of each of the hierarchical first and second feature maps may be determined separately. In an example, the first sub-loss may be determined based on a difference between the first feature map and a second feature map of the same resolution, e.g., the first sub-loss may be determined based on a difference in pixel values of each pixel point in the first feature map and a corresponding pixel point in the second feature map. The present disclosure does not limit the manner in which the first sub-loss is determined.
In one possible implementation, the first reconstruction result and the second reconstruction result further comprise a reconstruction image, respectively, the first reconstruction image and the second reconstruction image may have equal resolutions and may have equal resolutions to the sample color image. The second sub-loss may be determined based on differences between the first reconstructed image and the second reconstructed image, e.g., the second sub-loss may be determined based on differences in pixel values of pixels in the first reconstructed image and pixel values of corresponding pixels in the second reconstructed image. The present disclosure does not limit the manner in which the second sub-loss is determined.
In one possible implementation, each stage of the first sub-loss and the second sub-loss may be weighted and summed to obtain a first network loss. In the training process, the first network loss is reduced, so that each level of feature image output by the first reconstruction network for processing the dynamic visual information is more similar to the feature image output by the second reconstruction network for processing the color image, namely, the feature image corresponding to the dynamic visual information is more similar to the feature image corresponding to the color image, and further, the reconstructed image obtained based on the dynamic visual information is more similar to the real color image.
In one possible implementation, the training may make the feature map corresponding to the dynamic visual information and the feature map corresponding to the color image closer, and may make the second reconstructed image output by the second reconstruction network processing the color image closer to the real color image. In this way, the accuracy and fidelity of the second reconstructed image can be improved, and the accuracy and fidelity of the first reconstructed image close to the second reconstructed image can be improved, that is, the first reconstructed image can obtain an accurate and vivid reconstructed image.
In one possible implementation, the second network loss may be determined based on a difference between the second reconstructed image and the actual sample color image, e.g., the second network loss may be determined based on a difference in pixel values of pixels in the second reconstructed image and pixel values of corresponding pixels in the sample color image. The present disclosure does not limit the manner in which the second network loss is determined.
In one possible implementation manner, the first network loss and the second network loss may be integrated, so that the first feature map output by the first reconstruction network may approach the second feature map of the real sample color image step by step in the training process, and the first reconstructed image output by the first reconstruction network may approach the real sample color image step by step.
In one possible implementation, determining the integrated network loss from the first network loss and the second network loss includes: and carrying out weighted summation processing on the first network loss and the second network loss to obtain the comprehensive network loss. That is, the first network loss and the second network loss are weighted and summed, and the total network loss obtained by the weighted and summed is trained such that the total network loss is gradually reduced, that is, such that each level of the first feature map approaches the corresponding second feature map, such that the first reconstructed image approaches the second reconstructed image, and such that the second reconstructed image approaches the sample color image. That is, by the difference between the feature map, which is the first feature map, and the feature map of the true sample color image being reduced, the first reconstructed image is made more realistic and accurate, i.e., the first reconstructed image is made closer to the sample color image.
In one possible implementation, the training steps may be performed iteratively, and the trained first and second reconstruction networks are obtained when the training conditions are met. The training conditions may include a training number condition, that is, training is completed when the training step is iteratively performed for a preset number of times. Alternatively, the training condition may include whether the integrated network loss is less than or equal to a preset threshold or converges to a preset interval, and if the integrated network loss is less than or equal to the preset threshold or converges to the preset interval, the training may be completed.
In one possible implementation, the dynamic visual information may be processed through the trained first reconstruction network to generate a realistic and accurate color image.
In one possible implementation manner, the disclosure further relates to an image generating method, including: and inputting the dynamic visual information of the preset scene acquired at a plurality of moments in the first time period into a first reconstruction network trained according to the neural network training method for processing, and generating a first color image corresponding to each dynamic visual information.
In an example, the length of the first period may be equal to a time interval between two frames of color images (e.g., images or video frames) of the preset scene acquired by the camera or the camera, or may be a time interval between multiple frames of color images of the preset scene acquired. That is, the start-stop time of the first period may be the time at which the color image is acquired.
In another example, the start-stop time of the first period may not be the time when the color image is acquired, and the length of the first period may be smaller than the period between two frames of color images acquired by the camera or the video camera, which is only required to acquire at least one frame of color image in the first period. The present disclosure does not limit the length of the first time period and the starting time. For example, the start time of the first period may be before one frame of the color image is captured, and the end time of the first period may be after one frame of the color image is captured, and does not necessarily coincide with the time when the color image is captured.
In one possible implementation, the method further includes: and obtaining a video in the first time period of the preset scene according to the first color image and the second color image of the preset scene obtained in the first time period, wherein the obtaining frequency of the dynamic visual information is higher than that of the color image. That is, the first color image generated by the plurality of dynamic visual information acquired in the first period can supplement the second color image shot in the first period, that is, the number of the color images acquired in the first period is increased, so that the time interval between the color images in the first period is shorter, and more accurate video is acquired. So as to improve the observation and tracking effects on the target object in the preset scene, for example, the acquired action and/or movement track of the target object can be more accurate.
In one possible implementation, the second color image may not be captured in the first period, but a plurality of first color images may be generated only by captured dynamic visual information, and may constitute a video of the preset scene in the first period. The present disclosure does not limit whether to capture the second color image.
According to the neural network training method of the embodiment of the disclosure, the feature map corresponding to the dynamic visual information and the feature map corresponding to the color image can be more similar through training, and the second reconstructed image which is output by processing the color image by the second reconstructed network can be more similar to the real color image, namely, the accuracy degree and the fidelity degree of the second reconstructed image can be improved, and the accuracy degree and the fidelity degree of the first reconstructed image which is similar to the second reconstructed image can be further improved. Because the frequency of the dynamic visual information is higher than the acquisition frequency of the color image, the dynamic visual information is processed through the first reconstruction network, so that the acquisition frequency of the color image can be improved, the tracking of the motion trail or action of the moving object is facilitated, and the tracking effect is improved.
Fig. 2 illustrates an application diagram of a neural network training method according to an embodiment of the present disclosure, as illustrated in fig. 2, a first reconstruction network and a second reconstruction network may be trained with sample dynamic visual information and sample color images of the same scene.
In one possible implementation, the decoding subnetwork of the first reconstruction network includes three levels, two levels of first feature map and first reconstructed image can be output. The decoding sub-network of the second reconstruction network includes three levels, and can output two-level second feature images and second reconstructed images. The resolutions of the first feature map and the second feature map of each level are equal, and the resolutions of the first reconstructed image, the second reconstructed image and the sample color image are equal.
In one possible implementation, the first sub-loss 1 of the first stage may be determined from a difference between the first stage first feature map and the first stage second feature map, and the first sub-loss 2 of the second stage may be determined from a difference between the second stage first feature map and the second stage second feature map.
In one possible implementation, the second sub-loss 3 may be determined from a difference between the first reconstructed image and the second reconstructed image. The first network loss is obtained by weighted summing the first sub-loss 1, the first sub-loss 2, and the second sub-loss 3.
In one possible implementation, the second network loss4 may be determined from the difference between the second reconstructed image and the sample color image. And carrying out weighted summation on the first network loss and the second network loss to obtain the comprehensive network loss of the first reconstruction network and the second reconstruction network. In an example, the integrated network loss may be determined by the following equation 1:
Loss＝w 1 ×Loss 1 +w 2 ×Loss 2 +w 3 ×Loss 3 +w 4 ×Loss 4 (1)
Wherein w is 1 、w 2 、w 3 And w 4 Is a preset weight.
In one possible implementation, the first and second reconstructed networks may be trained by the integrated network loss, and the training may be completed when the integrated network loss is less than or equal to a preset threshold, or converges within a preset interval. The trained first reconstruction network may be used to process dynamic visual information to obtain a color image.
In one possible implementation, the neural network training method may be used to obtain a first reconstruction network capable of processing dynamic visual information to generate color images, and more color images may be generated by the first reconstruction network, so that the number of color images obtained in a predetermined period of time increases, and the time interval of the color images is smaller, which facilitates observation and tracking of a target. The application field of the neural network training method is not limited by the present disclosure.
Fig. 3 shows a block diagram of a neural network training device, as shown in fig. 3, including: the first reconstruction module 11 is configured to input sample dynamic visual information of a sample scene into a first reconstruction network for processing, so as to obtain a first reconstruction result, where the first reconstruction result includes a multi-stage first feature map and a first reconstructed image; a second reconstruction block 12, configured to input a sample color image of the sample scene into a second reconstruction network for processing, to obtain a second reconstruction result, where the second reconstruction result includes a multi-stage second feature map and a second reconstruction image, and the sample color image is the same as the acquisition time of the sample dynamic visual information; a loss determining module 13, configured to determine a comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result, and the second reconstruction result; a training module 14, configured to train the first reconstruction network and the second reconstruction network according to the comprehensive network loss, where the first reconstruction network is configured to generate a color image according to dynamic visual information, and the second reconstruction network is configured to train the first reconstruction network.
In one possible implementation, the loss determination module is further configured to: determining a first network loss according to the first reconstruction result and the second reconstruction result; determining a second network loss from the second reconstructed image and the sample color image; and determining the comprehensive network loss according to the first network loss and the second network loss.
In one possible implementation, the loss determination module is further configured to: determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map; determining a second sub-loss from the first reconstructed image and the second reconstructed image; and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
In one possible implementation, the first network loss and the second network loss are weighted and summed to obtain the integrated network loss.
In one possible implementation, the first reconstruction network includes a recurrent neural network and the second reconstruction network includes a convolutional neural network.
The present disclosure also relates to an image generation apparatus including: the generation module is used for inputting the dynamic visual information of the preset scene acquired at a plurality of moments in the first time period into the first reconstruction network trained by the neural network training method for processing, and generating a first color image corresponding to each dynamic visual information.
In one possible implementation, the apparatus further includes: the video generation module is used for obtaining videos in the first time period of the preset scene according to the first color image and the second color image of the preset scene obtained in the first time period, wherein the obtaining frequency of the dynamic visual information is higher than that of the color image.
It will be appreciated that the above-mentioned method embodiments of the present disclosure may be combined with each other to form a combined embodiment without departing from the principle logic, and are limited to the description of the present disclosure. It will be appreciated by those skilled in the art that in the above-described methods of the embodiments, the particular order of execution of the steps should be determined by their function and possible inherent logic.
In addition, the disclosure further provides a neural network training device, an electronic device, a computer readable storage medium and a program, which can be used for implementing any of the neural network training methods provided in the disclosure, and corresponding technical schemes and descriptions and corresponding records of method parts are omitted.
In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.
The disclosed embodiments also provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method. The computer readable storage medium may be a non-volatile computer readable storage medium.
The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.
Embodiments of the present disclosure also provide a computer program product comprising computer readable code which, when run on a device, causes a processor in the device to execute instructions for implementing the neural network training method provided in any of the embodiments above.
The disclosed embodiments also provide another computer program product for storing computer readable instructions that, when executed, cause a computer to perform the operations of the neural network training method provided in any of the above embodiments.
The electronic device may be provided as a terminal, server or other form of device.
Fig. 4 illustrates a block diagram of an electronic device 800, according to an embodiment of the disclosure. For example, electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.
Referring to fig. 4, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen between the electronic device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only an edge of a touch or slide action, but also a duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the electronic device 800. For example, the sensor assembly 814 may detect an on/off state of the electronic device 800, a relative positioning of the components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in position of the electronic device 800 or a component of the electronic device 800, the presence or absence of a user's contact with the electronic device 800, an orientation or acceleration/deceleration of the electronic device 800, and a change in temperature of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices, either wired or wireless. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including computer program instructions executable by processor 820 of electronic device 800 to perform the above-described methods.
Fig. 5 illustrates a block diagram of an electronic device 1900 according to an embodiment of the disclosure. For example, electronic device 1900 may be provided as a server. Referring to FIG. 5, electronic device 1900 includes a processing component 1922 that further includes one or more processors and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by processing component 1922. The application programs stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, processing component 1922 is configured to execute instructions to perform the methods described above.
The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate an operating system based on a memory 1932, such as Windows Server TM ，Mac OS X TM ，Unix TM ,Linux TM ，FreeBSD TM Or the like.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1932, including computer program instructions executable by processing component 1922 of electronic device 1900 to perform the methods described above.
The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (8)
1. A neural network training method, comprising:
inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing to obtain a first reconstruction result, wherein the first reconstruction result comprises a multi-stage first feature map and a first reconstruction image;
Inputting a sample color image of the sample scene into a second reconstruction network for processing to obtain a second reconstruction result, wherein the second reconstruction result comprises a multi-stage second feature image and a second reconstruction image, and the sample color image is the same as the acquisition time of the sample dynamic visual information;
determining a comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result;
training the first and second rebuilt networks based on the integrated network loss,
the first reconstruction network is used for generating a color image according to dynamic visual information, and the second reconstruction network is used for training the first reconstruction network;
determining a comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result, comprising:
determining a first network loss according to the first reconstruction result and the second reconstruction result;
determining a second network loss from the second reconstructed image and the sample color image;
Determining the integrated network loss based on the first network loss and the second network loss;
determining a first network loss according to the first reconstruction result and the second reconstruction result, including:
determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map;
determining a second sub-loss from the first reconstructed image and the second reconstructed image;
and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
2. The method of claim 1, wherein the first reconstruction network comprises a recurrent neural network and the second reconstruction network comprises a convolutional neural network.
3. An image generation method, comprising:
inputting dynamic visual information of a preset scene acquired at a plurality of moments in a first time period into a first reconstruction network for processing, and generating a first color image corresponding to each dynamic visual information, wherein the first reconstruction network is trained according to the neural network training method of any one of claims 1-2.
4. A method according to claim 3, characterized in that the method further comprises:
and obtaining a video in the first time period of the preset scene according to the first color image and the second color image of the preset scene obtained in the first time period, wherein the obtaining frequency of the dynamic visual information is higher than that of the color image.
5. A neural network training device, comprising:
the first reconstruction module is used for inputting sample dynamic visual information of a sample scene into a first reconstruction network for processing to obtain a first reconstruction result, wherein the first reconstruction result comprises a multi-stage first feature map and a first reconstruction image;
the second reconstruction module is used for inputting a sample color image of the sample scene into a second reconstruction network for processing to obtain a second reconstruction result, wherein the second reconstruction result comprises a multi-stage second feature map and a second reconstruction image, and the sample color image is identical to the acquisition time of the sample dynamic visual information;
the loss determination module is used for determining the comprehensive network loss of the first reconstruction network and the second reconstruction network according to the sample color image, the first reconstruction result and the second reconstruction result;
A training module for training the first and second reconstruction networks based on the integrated network loss,
the first reconstruction network is used for generating a color image according to dynamic visual information, and the second reconstruction network is used for training the first reconstruction network;
the loss determination module is further to: determining a first network loss according to the first reconstruction result and the second reconstruction result; determining a second network loss from the second reconstructed image and the sample color image; determining the integrated network loss based on the first network loss and the second network loss;
the loss determination module is further to: determining first sub-losses of each stage according to each stage of first feature map and a second feature map with the same resolution as each stage of first feature map; determining a second sub-loss from the first reconstructed image and the second reconstructed image; and carrying out weighted summation processing on the first sub-loss and the second sub-loss of each stage to obtain the first network loss.
6. An image generating apparatus, comprising:
the generating module is used for inputting the dynamic visual information of the preset scene acquired at a plurality of moments in the first time period into a first reconstruction network for processing, and generating a first color image corresponding to each dynamic visual information, wherein the first reconstruction network is trained by the neural network training device according to claim 5.
7. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 4.
8. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799904.5A CN113506229B (en) | 2021-07-15 | 2021-07-15 | Neural network training and image generating method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799904.5A CN113506229B (en) | 2021-07-15 | 2021-07-15 | Neural network training and image generating method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113506229A CN113506229A (en) | 2021-10-15 |
| CN113506229B true CN113506229B (en) | 2024-04-12 |
Family
ID=78012853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110799904.5A Active CN113506229B (en) | 2021-07-15 | 2021-07-15 | Neural network training and image generating method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506229B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377516A (en) * | 2018-11-01 | 2019-02-22 | 清华大学 | A kind of optical flow computation method using dynamic vision data |
| CN111462268A (en) * | 2020-03-31 | 2020-07-28 | 北京市商汤科技开发有限公司 | Image reconstruction method and device, electronic equipment and storage medium |
| CN111582300A (en) * | 2020-03-20 | 2020-08-25 | 北京航空航天大学 | High-dynamic target detection method based on event camera |
| WO2020186702A1 (en) * | 2019-03-18 | 2020-09-24 | 北京市商汤科技开发有限公司 | Image generation method and apparatus, electronic device, and storage medium |
| CN113096158A (en) * | 2021-05-08 | 2021-07-09 | 北京灵汐科技有限公司 | Moving object identification method and device, electronic equipment and readable storage medium |
-
2021
- 2021-07-15 CN CN202110799904.5A patent/CN113506229B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377516A (en) * | 2018-11-01 | 2019-02-22 | 清华大学 | A kind of optical flow computation method using dynamic vision data |
| WO2020186702A1 (en) * | 2019-03-18 | 2020-09-24 | 北京市商汤科技开发有限公司 | Image generation method and apparatus, electronic device, and storage medium |
| CN111582300A (en) * | 2020-03-20 | 2020-08-25 | 北京航空航天大学 | High-dynamic target detection method based on event camera |
| CN111462268A (en) * | 2020-03-31 | 2020-07-28 | 北京市商汤科技开发有限公司 | Image reconstruction method and device, electronic equipment and storage medium |
| CN113096158A (en) * | 2021-05-08 | 2021-07-09 | 北京灵汐科技有限公司 | Moving object identification method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113506229A (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658352B (en) | Image information optimization method and device, electronic equipment and storage medium | |
| CN113766313B (en) | Video data processing method and device, electronic equipment and storage medium | |
| CN109257645B (en) | Video cover generation method and device | |
| CN107944409B (en) | Video analysis method and device capable of distinguishing key actions | |
| CN110060215B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN111445414B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN111553864A (en) | Image restoration method and device, electronic equipment and storage medium | |
| CN111340733B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN112465843A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN111539410B (en) | Character recognition method and device, electronic equipment and storage medium | |
| CN111523346B (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN111369482B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110675355B (en) | Image reconstruction method and device, electronic equipment and storage medium | |
| CN110633715B (en) | Image processing method, network training method and device and electronic equipment | |
| CN109756783B (en) | Poster generation method and device | |
| CN113506324B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN109189822B (en) | Data processing method and device | |
| CN113506325B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110333903B (en) | Method and device for determining page loading duration | |
| CN112651880B (en) | Video data processing method and device, electronic equipment and storage medium | |
| CN113506229B (en) | Neural network training and image generating method and device | |
| CN113506321A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN113506323B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110896492B (en) | Image processing method, device and storage medium | |
| CN113506319B (en) | Image processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |