CN112200732B - Video deblurring method with clear feature fusion - Google Patents
Video deblurring method with clear feature fusion Download PDFInfo
- Publication number
- CN112200732B CN112200732B CN202010368483.6A CN202010368483A CN112200732B CN 112200732 B CN112200732 B CN 112200732B CN 202010368483 A CN202010368483 A CN 202010368483A CN 112200732 B CN112200732 B CN 112200732B
- Authority
- CN
- China
- Prior art keywords
- clear
- feature
- deblurring
- frames
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000004927 fusion Effects 0.000 title claims abstract description 14
- 230000003287 optical effect Effects 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 3
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- 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
Abstract
The invention discloses a video deblurring method with fused clear features. Firstly, selecting a plurality of continuous fuzzy video frames, estimating optical flow between the continuous frames by using an optical flow estimation network, twisting images of adjacent frames by using the estimated optical flow, then taking a twisted result and an original fuzzy frame sequence as input of a deblurring network, then selecting a plurality of clear frames, passing through a clear feature extraction module, obtaining clear features, fusing the clear features into the deblurring network, and finally outputting relatively clear video frames by the deblurring network. The method is robust to scenes with clear frames, clear frames of any scene can be used for feature fusion, and reconstruction of video frames is facilitated, so that the method is convenient and effective.
Description
Technical Field
The invention relates to an end-to-end video deblurring network, in particular to a video deblurring algorithm based on clear feature fusion.
Background
In recent years, with the development of portable imaging devices, such as mobile phones and cameras, image/video deblurring techniques have received increased attention. The reasons for the formation of blur are many, including the motion of the object during imaging, the shake of the camera and the depth of field, which provide much resistance to the study of computer vision (object detection, object recognition). Therefore, it is very necessary to research the deblurring algorithm.
At present, the deblurring algorithm is mainly divided into two types, one type is a method based on a physical model, and the other type is a method based on learning. Early, according to a degradation model (B = K × S + N), where B denotes a blurred image, K denotes a blur kernel, S denotes a sharp image, and N denotes additive noise. In the case of the known blurred image B, it is very difficult to solve the blurred kernel K and the sharp image S, and a multi-solution situation may occur, so that the problem is ill-conditioned. In order to constrain the solution space, people design some natural image priors, including L0 gradient priors, dark channel priors, etc., to constrain the natural image, and solve under a maximum posterior framework. However, the method is difficult to optimize based on a physical model, time-consuming, without universality, and requires artificially designed prior information for constraint.
Another learning-based approach is the one that is currently more popular. People learn the internal distribution of natural images from data sets through a reasonable neural network, and finally achieve the aim of deblurring.
The invention provides an end-to-end video deblurring network, which is different from image deblurring, and the video deblurring needs to consider the relation between adjacent frames.
Disclosure of Invention
The invention aims to provide an end-to-end video deblurring algorithm based on clear feature fusion, which is used for inputting a plurality of continuous blurred video frames and recovering clear intermediate frames.
The technical solution for realizing the purpose of the invention is as follows: a video deblurring algorithm based on sharp feature fusion comprises the following steps:
step A: designing an optical flow estimation module, inputting three continuously blurred frames into the optical flow estimation module, and outputting a result obtained by performing image torsion (image warp) on two adjacent frames;
and B, step B: designing a clear feature fusion module, inputting any clear three frames into the module, and outputting clear feature graphs with different scales;
step C: designing a deblurring module, stacking the result of the step A and the original input and then sending the result into the module, and fusing the result of the step B into the whole deblurring process to finally obtain a clear intermediate frame.
Compared with the prior art, the invention has the following remarkable advantages: the invention considers the motion compensation and the image deblurring at the same time. The method is robust to scenes with clear frames, clear frames of any scene can be used for feature fusion, reconstruction of video frames is facilitated, and the method is convenient and effective.
Drawings
FIG. 1 is an overall flow diagram of the present invention.
Fig. 2 is a diagram of a network architecture designed by the present invention.
FIG. 3 is a comparison graph of the deblurring effect of the present invention. The (a) is the blurred video frame, and the (b) is the reconstruction result.
Detailed Description
The invention is further described in the following with reference to the drawings.
As shown in fig. 2, the whole network includes 3 modules, which are an optical flow estimation module, a sharp feature fusion module and a deblurring module.
According to the first panel of fig. 1, the data preparation steps are as follows:
step 1, downloading a GOPRO _ Su data set as a training sample, wherein the GOPRO _ Su data set comprises 71 video sets, and each video is provided with a plurality of paired fuzzy-clear video frames;
and 2, dividing 71 videos into two parts, wherein 61 videos serve as training samples, and 10 videos serve as testing samples.
According to the second block of fig. 1, the steps of the optical flow estimation module are as follows:
step 1, presetting training parameters, including a learning rate 1e-6 of an optical flow estimation module, a learning rate 1e-4 of a deblurring module, and maximum iteration epoch =500;
f 1→2 =F([I 1 ,I 2 ]),f 3→2 =F([I 3 ,I 2 ]),
warp 1→2 =W([f 1→2 ,I 1 ]),warp 3→2 =W([f 3→2 ,I 3 ]);
where F () denotes an optical flow estimation network, [ ] denotes the operation of image concat, and W () denotes warp operation.
According to the third panel of fig. 1, the steps of the sharp feature fusion module are as follows:
selecting three clear images (S) 1 ,S 2 ,S 3 The three clear images are passed through a feature extraction module, which is composed of two layers of convolution respectively, to finally obtain 32256 pieces of 256 × 256 feature maps { feature _ coarse } and 64 pieces of 64 × 64 feature maps { feature _ fine }. The process can be described as follows:
Feature_coarse,feature_fine=E([S 1 ,S 2 ,S 3 ])
where E () represents the feature extraction network and [ ] represents the operation of the image concat.
According to the fourth panel of fig. 1, the step of deblurring the module is as follows:
step 1, obtaining a warp result { warp ] in an optical flow estimation module 1→2 ,warp 3→2 And original blurred video frame { I } 1 ,I 2 ,I 3 Sending the fuzzy data into a deblurring module;
and 2, the deblurring module is a coding and decoding structure, wherein each coding block is formed by adding three residual blocks to 1-layer convolution, and each decoding block is formed by adding one deconvolution to the three residual blocks. In the process of deblurring, embedding the clear feature map { feature _ coarse, feature _ fine } obtained by the clear feature fusion module into an encoder part and a decoder part in the deblurring module to finally obtain a feature I 2 Corresponding sharp image R 2 . Clear image R generated by calculation 2 With the original I 2 Reference sharp image G 2 To update the entire network. The process can be described as follows:
input=[warp 1→2 ,I 1 ,I 2 ,I 3 ,warp 3→2 ],
En_out=En(input,feature_coarse,feature_fine),
De_out=De(En_out,feature_coarse,feature_fine);
where En () represents the encoder portion and De () represents the decoder portion.
And 3, training according to the steps until the maximum iteration number is reached, and finishing training when the generated model is reached.
According to the fifth panel of fig. 1, the test procedure is as follows:
step 1, inputting 10 video test samples obtained by a data preparation part into a trained model;
and 2, selecting the clear frame, namely selecting any clear frame different from the fuzzy scene, and inputting the clear frame into the trained model to finally obtain a clear image. Fig. 3 is a diagram of the visual effect of the present invention.
Claims (3)
1. A video deblurring method based on clear feature fusion specifically comprises the following steps
Step A: designing an optical flow estimation module, inputting three continuous fuzzy frames into the optical flow estimation module, and outputting a result obtained by image torsion image warp of two adjacent frames;
and B: designing a clear feature fusion module, inputting any clear three frames into the clear feature fusion module, and outputting clear feature graphs of different scales;
step C: designing a deblurring module, stacking the result of the step A and three continuous blurred frames, sending the result into the deblurring module, and fusing the result of the step B into the whole deblurring process to finally obtain a clear intermediate frame; the step C specifically comprises the following steps:
step C01. Obtaining a result { warp after warp obtained in step A02 1→2 ,warp 3→2 And original blurred video frame { I } 1 ,I 2 ,I 3 Sending the fuzzy data into a deblurring module; in the process of deblurring, embedding the clear feature map { feature _ coarse, feature _ fine } obtained in the step B01 into a deblurring module to finally obtain a feature map I 2 Corresponding sharp image R 2 (ii) a Clear image R generated by calculation 2 With original I 2 Reference sharp image G 2 To update the entire network;
c02, training according to the step C01 until the maximum iteration number is reached, and finishing training when the generated model is reached;
and C03, after the model training is finished, inputting three continuous fuzzy frames, and selecting any clear frame to extract clear features to finally obtain a clear image.
2. The method of claim 1, wherein step a specifically comprises the steps of:
a01, presetting training parameters, including a learning rate 1e-6 of an optical flow estimation module, a learning rate 1e-4 of a deblurring module, and maximum iteration epoch =500;
step A02. Selecting three continuous blurred images { I 1 ,I 2 ,I 3 Estimating the optical flow between two adjacent frames by FlowNet S 1→2 ,flow 3→2 Obtaining two 2-channel optical flow graphs respectively, performing image torsion (image warp) operation on the optical flow and an adjacent frame, and twisting the adjacent frame to an intermediate frame to finally obtain two 3-channel RGB images { warp 1→2 ,warp 3→2 }。
3. The method of claim 1, wherein step B specifically comprises the steps of:
step B01, selecting three clear images { S 1 ,S 2 ,S 3 And the three clear images are different from the content of the blurred image in the step A02, and the three clear images are passed through a feature extraction module to obtain 32 256 × 256 feature maps { feature _ coarse } and 64 × 64 feature maps { feature _ fine } respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010368483.6A CN112200732B (en) | 2020-04-30 | 2020-04-30 | Video deblurring method with clear feature fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010368483.6A CN112200732B (en) | 2020-04-30 | 2020-04-30 | Video deblurring method with clear feature fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112200732A CN112200732A (en) | 2021-01-08 |
CN112200732B true CN112200732B (en) | 2022-10-21 |
Family
ID=74005893
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010368483.6A Active CN112200732B (en) | 2020-04-30 | 2020-04-30 | Video deblurring method with clear feature fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112200732B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112767250B (en) * | 2021-01-19 | 2021-10-15 | 南京理工大学 | Video blind super-resolution reconstruction method and system based on self-supervision learning |
CN114066751B (en) * | 2021-10-29 | 2024-02-27 | 西北工业大学 | Vehicle card monitoring video deblurring method based on common camera acquisition condition |
CN115170400A (en) * | 2022-04-06 | 2022-10-11 | 腾讯科技(深圳)有限公司 | Video repair method, related device, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103914810A (en) * | 2013-01-07 | 2014-07-09 | 通用汽车环球科技运作有限责任公司 | Image super-resolution for dynamic rearview mirror |
CN109461131A (en) * | 2018-11-20 | 2019-03-12 | 中山大学深圳研究院 | A kind of real-time deblurring method of intelligent inside rear-view mirror based on neural network algorithm |
CN110062164A (en) * | 2019-04-22 | 2019-07-26 | 深圳市商汤科技有限公司 | Method of video image processing and device |
-
2020
- 2020-04-30 CN CN202010368483.6A patent/CN112200732B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103914810A (en) * | 2013-01-07 | 2014-07-09 | 通用汽车环球科技运作有限责任公司 | Image super-resolution for dynamic rearview mirror |
CN109461131A (en) * | 2018-11-20 | 2019-03-12 | 中山大学深圳研究院 | A kind of real-time deblurring method of intelligent inside rear-view mirror based on neural network algorithm |
CN110062164A (en) * | 2019-04-22 | 2019-07-26 | 深圳市商汤科技有限公司 | Method of video image processing and device |
Also Published As
Publication number | Publication date |
---|---|
CN112200732A (en) | 2021-01-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111062872B (en) | Image super-resolution reconstruction method and system based on edge detection | |
CN112200732B (en) | Video deblurring method with clear feature fusion | |
CN111028177B (en) | Edge-based deep learning image motion blur removing method | |
CN111709895A (en) | Image blind deblurring method and system based on attention mechanism | |
CN112419151B (en) | Image degradation processing method and device, storage medium and electronic equipment | |
CN112233038A (en) | True image denoising method based on multi-scale fusion and edge enhancement | |
CN110933429B (en) | Video compression sensing and reconstruction method and device based on deep neural network | |
CN109636721B (en) | Video super-resolution method based on countermeasure learning and attention mechanism | |
CN112801901A (en) | Image deblurring algorithm based on block multi-scale convolution neural network | |
CN111539884A (en) | Neural network video deblurring method based on multi-attention machine mechanism fusion | |
CN114463218B (en) | Video deblurring method based on event data driving | |
Guo et al. | Dense123'color enhancement dehazing network | |
CN113066022B (en) | Video bit enhancement method based on efficient space-time information fusion | |
CN116681584A (en) | Multistage diffusion image super-resolution algorithm | |
CN113724136A (en) | Video restoration method, device and medium | |
CN113379606B (en) | Face super-resolution method based on pre-training generation model | |
CN117333398A (en) | Multi-scale image denoising method and device based on self-supervision | |
CN112598604A (en) | Blind face restoration method and system | |
CN116883265A (en) | Image deblurring method based on enhanced feature fusion mechanism | |
CN117058043A (en) | Event-image deblurring method based on LSTM | |
CN116433516A (en) | Low-illumination image denoising and enhancing method based on attention mechanism | |
CN115797646A (en) | Multi-scale feature fusion video denoising method, system, device and storage medium | |
CN111524060B (en) | System, method, storage medium and device for blurring portrait background in real time | |
CN115841523A (en) | Double-branch HDR video reconstruction algorithm based on Raw domain | |
CN115293988A (en) | Image deblurring method and system based on deep learning |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Xiang Xinguang Inventor after: Wei Hao Inventor after: Pan Jinshan Inventor before: Wei Hao Inventor before: Xiang Xinguang Inventor before: Pan Jinshan |
|
GR01 | Patent grant | ||
GR01 | Patent grant |