CN112651911A - High dynamic range imaging generation method based on polarization image - Google Patents
High dynamic range imaging generation method based on polarization image Download PDFInfo
- Publication number
- CN112651911A CN112651911A CN202011388884.4A CN202011388884A CN112651911A CN 112651911 A CN112651911 A CN 112651911A CN 202011388884 A CN202011388884 A CN 202011388884A CN 112651911 A CN112651911 A CN 112651911A
- Authority
- CN
- China
- Prior art keywords
- polarization
- image
- hdr
- images
- generation model
- 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.)
- Granted
Links
- 230000010287 polarization Effects 0.000 title claims abstract description 162
- 238000003384 imaging method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 230000004313 glare Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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 using two or more images, e.g. averaging or subtraction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/741—Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
-
- 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]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a high dynamic range imaging generation method based on a polarization image, which comprises the following steps: aiming at a target area needing imaging, acquiring a plurality of polarization images with different polarization angles through single exposure of a polarization camera; constructing an HDR generation model, using a plurality of polarization images with different polarization angles as HDR generation model input, using the HDR generation model to learn the characteristics of the polarization images and the characteristics of polarization effects, and finally outputting a characteristic image of each polarization image by the HDR generation model; calculating linear polarization degree characteristics and polarization angle characteristics by using the polarization image; and fusing the characteristic images of all polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters. The method obtains the HDR image through network learning and polarization degree characteristics and the like, does not need a plurality of images with different exposure time, can obtain the HDR image through single exposure, effectively reduces the problem of image ghosting caused by fusion of a plurality of images, and improves the imaging effect.
Description
Technical Field
The application relates to the technical field of high dynamic range imaging, in particular to a high dynamic range imaging generation method based on a polarization image.
Background
High Dynamic Range Imaging (HDR) is a group of techniques for realizing a larger exposure Dynamic Range than the general digital image technique, and is widely used in the fields of computer graphics, image photography, and the like. The common digital image has only 256 brightness levels, which is far inferior to the perception range of human eyes, so that the HDR image can provide more dynamic range and image details, so that the HDR image better reflects the visual effect in the real environment of human beings. The traditional HDR imaging is mainly to take a plurality of images with different exposure times, and synthesize a final HDR image by using the optimal details corresponding to each exposure time; however, the conventional HDR imaging method is prone to image ghosting in the process of image fusion of a plurality of images with different exposure times, and the imaging effect needs to be improved.
Disclosure of Invention
The application aims to provide a high dynamic range imaging generation method based on a polarization image, which is used for overcoming the problems of easy ghost generation and poor imaging effect of the existing HDR imaging.
In order to realize the task, the following technical scheme is adopted in the application:
in a first aspect, the present application provides a method for generating high dynamic range imaging based on polarization images, including:
aiming at a target area needing imaging, acquiring a plurality of polarization images with different polarization angles through single exposure of a polarization camera;
constructing an HDR generation model, using a plurality of polarization images with different polarization angles as HDR generation model input, using the HDR generation model to learn the characteristics of the polarization images and the characteristics of polarization effects, and finally outputting a characteristic image of each polarization image by the HDR generation model;
calculating linear polarization degree characteristics and polarization angle characteristics by using the polarization image;
and fusing the characteristic images of all polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters.
Further, the polarization images with different polarization angles are polarization images with 4 polarization angles of 0 °, 45 °, 90 ° and 135 °.
Further, the calculation formula of the polarization degree characteristic P1 and the polarization angle characteristic P2 is as follows:
in the above formula, I0,I45,I90,I135The intensities of the polarization images acquired at the polarization angles of 0 °, 45 °, 90 °, and 135 °, respectively.
Further, the HDR generation model is constructed using a convolutional neural network; the HDR generation model adopts a structure of an encoder and a decoder, wherein the down-sampling structure of the encoder is used for extracting the characteristics of the polarized image, and the decoder restores the characteristics of the image to the size of the original image; in the model, the granularity roughness of upsampling is improved by introducing jump connection from a high-resolution feature map.
Further, a loss function of the HDR generation model is constructed, so that the output of the model approaches to a true value of the HDR image; the loss function is expressed as:
in the above formula,. mu.x、
Mean, standard deviation, μ of a feature map representing the polarization image x output by the modely、
Representing the mean, standard deviation, σ, of the image truth values corresponding to the polarization image xxyRepresenting the covariance of the truth values of the feature map, image, C1、C2Is a constant.
In a second aspect, the present application provides a polarization image-based high dynamic range imaging generation apparatus, comprising:
the acquisition module is used for acquiring a plurality of polarization images with different polarization angles through single exposure of the polarization camera aiming at a target area to be imaged;
the model building module is used for building an HDR generation model, a plurality of polarization images with different polarization angles are used as the input of the HDR generation model, the characteristics of the polarization images and the characteristics of polarization effects are learned by using the HDR generation model, and finally the HDR generation model outputs the characteristic diagram of each polarization image;
the characteristic calculation module is used for calculating linear polarization degree characteristics and polarization angle characteristics by utilizing the polarization images;
and the image fusion module is used for fusing the characteristic images of all the polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters.
In a third aspect, the present application provides a terminal device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the polarization image-based high dynamic range imaging generation method of the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for generating polarization image-based high dynamic range imaging of the first aspect.
Compared with the prior art, the method has the following technical characteristics:
1. the method is different from the scheme that the existing high dynamic range imaging technology needs a plurality of images with different exposure times to be fused, different polarization images captured by a polarization camera in a single exposure are used as network input, the HDR images are obtained through network learning and polarization degree characteristics, the HDR images can be obtained through the single exposure without the need of the plurality of images with different exposure times, and the problems of image ghosting and the like caused by the fusion of the plurality of images are effectively reduced.
2. Compared with the existing HDR method for generating a single image based on a deep learning model, the method makes full use of the characteristic that a polarization camera can filter glare on the surface of an object, restores the original image information on the surface of the object, and improves the imaging effect, so that the method has more advantages in HDR imaging.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present application;
FIG. 2 is a schematic diagram of four images captured at different polarization angles in an embodiment of the present application;
FIG. 3 is a schematic diagram of an HDR generative model;
FIG. 4 is a schematic diagram of an HDR fusion process;
fig. 5 is a schematic diagram of a polarization camera filtering glare on the surface of an object to recover information on the surface of the object according to an embodiment of the present disclosure.
Detailed Description
The strong learning ability of the deep learning enables the image to show more excellent performance in the image field than the traditional image processing method, so that the HDR image generated by combining the single exposure image and the deep learning has great research potential, and the defects of the traditional HDR image can be overcome.
The application provides a degree of polarization characteristic is calculated through single exposure polarization photo that polarization camera caught, polarization angle characteristic isoparametric, combines polarization image training high dynamic range imaging degree of depth learning model, finally can generate HDR image to the degree of depth learning model of single exposure image synthesis high dynamic image.
Referring to fig. 1, a method for generating high dynamic range imaging based on polarization image according to the present application includes the following steps:
step 1, aiming at a target area needing imaging, a plurality of polarization images with different polarization angles are obtained through single exposure of a polarization camera.
The polarization camera can capture four images with different polarization angles at a time, approximately view the images as images with different exposure time, and the polaroid can effectively reduce the original surface information of the object by the glare in the scene.
Due to the existence of the polarization effect of light, the amplitudes of corresponding pixels of four polarization images captured by a polarization camera from a non-uniform polarization scene are different, and the illumination intensity is attenuated due to the different angles of the polarizers on the four pixels; as shown in fig. 2, the ground in the image is not exposed to the same degree in each image due to the polarization effect.
Capturing polarized images using a polarized camera can be understood as imaging the same scene at different exposure times, so that there is a possibility to generate HDR images from four polarized images. Since the four radiance values are measured at four pixels and the filtering effect of the polarizer will cause one of the four pixels to be in the non-overexposed area, the HDR image will get a considerable improvement in the dark or underexposed areas.
And 2, constructing an HDR generation model by adopting a convolutional neural network, using a plurality of polarization images with different polarization angles as HDR generation model input, learning the characteristics of the polarization images and the characteristics of polarization effects by using the HDR generation model, and finally outputting the characteristic diagram of each polarization image by using the HDR generation model.
And 3, calculating a linear polarization degree characteristic P1 and a polarization angle characteristic P2 by using the polarization image.
And 4, fusing feature maps of all polarization images output by the HDR generation model into an HDR image by using a fusion algorithm by using P1 and P2 as fusion parameters.
In the embodiment of the present application, a single exposure of the polarization camera acquires polarization images of 4 polarization angles, which are 0 °, 45 °, 90 °, and 135 °, and then the calculation formulas of the polarization degree feature P1 and the polarization angle feature P2 are as follows:
in the above formula, I0,I45,I90,I135The intensities of the polarization images acquired at the polarization angles of 0 °, 45 °, 90 °, and 135 °, respectively.
The HDR generation model employs an encoder-decoder structure, as shown in fig. 3, where the downsampling structure of the encoder can extract the features of the polarized image, and the decoder restores the features of the image to the original image size. Since upsampling can cause image information to be lost, the scheme introduces jump connection from the high-resolution feature map to improve the granularity roughness of upsampling. Constructing a loss function of an HDR generation model to enable the output of the model to approach to the true value of an HDR image; the loss function in this scheme is constructed as follows:
in the above formula,. mu.x、
Mean, standard deviation, μ of a feature map representing the polarization image x output by the modely、
Representing the mean, standard deviation, σ, of the image truth values corresponding to the polarization image xxyRepresenting the covariance of the truth values of the feature map, image, C1、C2Is a constant.
As shown in fig. 4, after obtaining the feature map output by the HDR generation model for each polarization image, the feature map, the polarization degree feature P1, and the polarization angle feature P2 are combined and fused to obtain a final HDR image.
The scheme makes full use of the characteristic that the polarization camera can filter the glare on the surface of the object, reduces the original image information on the surface of the object, and recovers the lost information of the over-exposure area, as shown in fig. 5.
According to another aspect of the present application, there is provided a polarization image-based high dynamic range imaging generation apparatus, comprising:
the acquisition module is used for acquiring a plurality of polarization images with different polarization angles through single exposure of the polarization camera aiming at a target area to be imaged;
the model building module is used for building an HDR generation model, a plurality of polarization images with different polarization angles are used as the input of the HDR generation model, the characteristics of the polarization images and the characteristics of polarization effects are learned by using the HDR generation model, and finally the HDR generation model outputs the characteristic diagram of each polarization image;
the characteristic calculation module is used for calculating linear polarization degree characteristics and polarization angle characteristics by utilizing the polarization images;
and the image fusion module is used for fusing the characteristic images of all the polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters.
It should be noted that the specific execution steps of the modules are the same as the corresponding steps in the foregoing method embodiments, and are not described herein again.
The embodiment of the application further provides a terminal device, which can be a computer or a server; comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-described method for generating a polarized image based high dynamic range image when executing the computer program.
The computer program may also be partitioned into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present application. One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, where the instruction segments are used to describe an execution process of a computer program in a terminal device, for example, the computer program may be divided into an obtaining module, a model building module, a feature calculating module, and an image fusion module, and functions of each module are described in the foregoing apparatuses and are not described again.
Implementations of the present application provide a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, performs the steps of the above-described polarization image-based high dynamic range imaging generation method.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiment described above can be realized by the present application, and can also be completed by instructing the relevant hardware through a computer program. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer memory, read only memory ROM, random access memory RAM, electrical carrier signals, telecommunications signals, and software distribution media, etc.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (8)
1. A method for generating high dynamic range imaging based on polarization images, comprising:
aiming at a target area needing imaging, acquiring a plurality of polarization images with different polarization angles through single exposure of a polarization camera;
constructing an HDR generation model, using a plurality of polarization images with different polarization angles as HDR generation model input, using the HDR generation model to learn the characteristics of the polarization images and the characteristics of polarization effects, and finally outputting a characteristic image of each polarization image by the HDR generation model;
calculating linear polarization degree characteristics and polarization angle characteristics by using the polarization image;
and fusing the characteristic images of all polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters.
2. The method according to claim 1, wherein the plurality of polarization images with different polarization angles are polarization images with 4 polarization angles of 0 °, 45 °, 90 °, and 135 °.
3. The generation method of high dynamic range imaging based on polarized image as claimed in claim 2, wherein the calculation formula of the polarization degree characteristic P1 and the polarization angle characteristic P2 is as follows:
in the above formula, I0,I45,I90,I135The intensities of the polarization images acquired at the polarization angles of 0 °, 45 °, 90 °, and 135 °, respectively.
4. A polarized image based high dynamic range imaging generation method as claimed in claim 1, wherein the HDR generation model is constructed using a convolutional neural network; the HDR generation model adopts a structure of an encoder and a decoder, wherein the down-sampling structure of the encoder is used for extracting the characteristics of the polarized image, and the decoder restores the characteristics of the image to the size of the original image; in the model, the granularity roughness of upsampling is improved by introducing jump connection from a high-resolution feature map.
5. The method of claim 1, wherein the model output approximates the true value of the HDR image by constructing a loss function of the HDR generation model; the loss function is expressed as:
in the above formula,. mu.x、
Mean, standard deviation, μ of a feature map representing the polarization image x output by the modely、
Representing the mean, standard deviation, σ, of the image truth values corresponding to the polarization image xxyRepresenting the covariance of the truth values of the feature map, image, C1、C2Is a constant.
6. A polarized image based high dynamic range imaging generating apparatus, comprising:
the acquisition module is used for acquiring a plurality of polarization images with different polarization angles through single exposure of the polarization camera aiming at a target area to be imaged;
the model building module is used for building an HDR generation model, a plurality of polarization images with different polarization angles are used as the input of the HDR generation model, the characteristics of the polarization images and the characteristics of polarization effects are learned by using the HDR generation model, and finally the HDR generation model outputs the characteristic diagram of each polarization image;
the characteristic calculation module is used for calculating linear polarization degree characteristics and polarization angle characteristics by utilizing the polarization images;
and the image fusion module is used for fusing the characteristic images of all the polarization images output by the HDR generation model into an HDR image by taking the polarization degree characteristic and the polarization angle characteristic as fusion parameters.
7. A terminal device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that the processor, when executing the computer program, implements the steps of the polarization image based high dynamic range imaging generation method according to any of claims 1 to 5.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for generating polarized image based high dynamic range imaging according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388884.4A CN112651911B (en) | 2020-12-01 | 2020-12-01 | High dynamic range imaging generation method based on polarized image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388884.4A CN112651911B (en) | 2020-12-01 | 2020-12-01 | High dynamic range imaging generation method based on polarized image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112651911A true CN112651911A (en) | 2021-04-13 |
| CN112651911B CN112651911B (en) | 2023-10-13 |
Family
ID=75350062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011388884.4A Active CN112651911B (en) | 2020-12-01 | 2020-12-01 | High dynamic range imaging generation method based on polarized image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651911B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487504A (en) * | 2021-07-01 | 2021-10-08 | 天津大学 | Underwater gray level polarization image restoration method based on generation countermeasure network |
| CN113962915A (en) * | 2021-10-20 | 2022-01-21 | 哈尔滨工业大学 | Self-adaptive nonlinear super-dynamic image synthesis method under non-uniform illumination condition |
| CN115376009A (en) * | 2022-06-09 | 2022-11-22 | 中国矿业大学(北京) | Shadow vegetation extraction method and system based on polarization image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657965A (en) * | 2015-03-12 | 2015-05-27 | 长春理工大学 | Polarized image fusion method based on discrete continuous curvelet |
| EP2889807A2 (en) * | 2013-12-24 | 2015-07-01 | Ricoh Company, Ltd. | Image processing device, image processing system, mobile object control apparatus, image processing method, and carrier means |
| CN105139367A (en) * | 2015-07-27 | 2015-12-09 | 中国科学院光电技术研究所 | Visible light polarization image fusion method based on non-subsampled shear wave |
| CN111669514A (en) * | 2020-06-08 | 2020-09-15 | 北京大学 | High dynamic range imaging method and apparatus |
| CN111986129A (en) * | 2020-06-30 | 2020-11-24 | 普联技术有限公司 | HDR image generation method and device based on multi-shot image fusion and storage medium |
-
2020
- 2020-12-01 CN CN202011388884.4A patent/CN112651911B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2889807A2 (en) * | 2013-12-24 | 2015-07-01 | Ricoh Company, Ltd. | Image processing device, image processing system, mobile object control apparatus, image processing method, and carrier means |
| CN104657965A (en) * | 2015-03-12 | 2015-05-27 | 长春理工大学 | Polarized image fusion method based on discrete continuous curvelet |
| CN105139367A (en) * | 2015-07-27 | 2015-12-09 | 中国科学院光电技术研究所 | Visible light polarization image fusion method based on non-subsampled shear wave |
| CN111669514A (en) * | 2020-06-08 | 2020-09-15 | 北京大学 | High dynamic range imaging method and apparatus |
| CN111986129A (en) * | 2020-06-30 | 2020-11-24 | 普联技术有限公司 | HDR image generation method and device based on multi-shot image fusion and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李世维;黄丹飞;刘辉;王惠敏;: "基于多尺度边缘表示的偏振图像二次融合算法", 激光与红外, no. 01, pages 115 - 120 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487504A (en) * | 2021-07-01 | 2021-10-08 | 天津大学 | Underwater gray level polarization image restoration method based on generation countermeasure network |
| CN113487504B (en) * | 2021-07-01 | 2022-12-09 | 天津大学 | Underwater gray level polarization image restoration method based on generation countermeasure network |
| CN113962915A (en) * | 2021-10-20 | 2022-01-21 | 哈尔滨工业大学 | Self-adaptive nonlinear super-dynamic image synthesis method under non-uniform illumination condition |
| CN113962915B (en) * | 2021-10-20 | 2022-04-29 | 哈尔滨工业大学 | Self-adaptive nonlinear super-dynamic image synthesis method under non-uniform illumination condition |
| CN115376009A (en) * | 2022-06-09 | 2022-11-22 | 中国矿业大学(北京) | Shadow vegetation extraction method and system based on polarization image |
| CN115376009B (en) * | 2022-06-09 | 2023-04-18 | 中国矿业大学(北京) | Shadow vegetation extraction method and system based on polarization image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112651911B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428366B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| Jiang et al. | Learning to see moving objects in the dark | |
| CN109636754B (en) | Extremely-low-illumination image enhancement method based on generation countermeasure network | |
| WO2021179820A1 (en) | Image processing method and apparatus, storage medium and electronic device | |
| Zheng et al. | Learning frequency domain priors for image demoireing | |
| Zhao et al. | Pyramid global context network for image dehazing | |
| CN112651911B (en) | High dynamic range imaging generation method based on polarized image | |
| CN101422035B (en) | Light source estimation device, light source estimation system, light source estimation method, device having increased image resolution, and method for increasing image resolution | |
| WO2020152521A1 (en) | Systems and methods for transforming raw sensor data captured in low-light conditions to well-exposed images using neural network architectures | |
| US20220148297A1 (en) | Image fusion method based on fourier spectrum extraction | |
| Raghavendra et al. | Comparative evaluation of super-resolution techniques for multi-face recognition using light-field camera | |
| CN111986084A (en) | Multi-camera low-illumination image quality enhancement method based on multi-task fusion | |
| CN110276831B (en) | Method and device for constructing three-dimensional model, equipment and computer-readable storage medium | |
| WO2021179764A1 (en) | Image processing model generating method, processing method, storage medium, and terminal | |
| An et al. | Single-shot high dynamic range imaging via deep convolutional neural network | |
| Duan et al. | Guided event filtering: Synergy between intensity images and neuromorphic events for high performance imaging | |
| Aakerberg et al. | RELLISUR: A real low-light image super-resolution dataset | |
| CN112750092A (en) | Training data acquisition method, image quality enhancement model and method and electronic equipment | |
| Del Gallego et al. | Multiple-image super-resolution on mobile devices: an image warping approach | |
| Zhang et al. | Deep motion blur removal using noisy/blurry image pairs | |
| CN114511487A (en) | Image fusion method and device, computer readable storage medium and terminal | |
| Zhou et al. | Deblurring low-light images with events | |
| CN114298942A (en) | Image deblurring method and device, computer readable medium and electronic equipment | |
| CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
| CN107392986A (en) | A kind of image depth rendering intent based on gaussian pyramid and anisotropic filtering |
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 |