CN107154064A - Natural image compressed sensing method for reconstructing based on depth sparse coding - Google Patents
Natural image compressed sensing method for reconstructing based on depth sparse coding Download PDFInfo
- Publication number
- CN107154064A CN107154064A CN201710306725.7A CN201710306725A CN107154064A CN 107154064 A CN107154064 A CN 107154064A CN 201710306725 A CN201710306725 A CN 201710306725A CN 107154064 A CN107154064 A CN 107154064A
- Authority
- CN
- China
- Prior art keywords
- conversion coefficient
- observation
- training
- image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of natural image compressed sensing method for reconstructing based on depth sparse coding, the problem of existing method is difficult to fast, accurately use coefficient reconstruction natural image is mainly solved.Its implementation is:1) to image block and in orthogonal transform domain up conversion, the observation vector of calculation of transform coefficients;2) the recovery conversion coefficient of observation vector is obtained with iteration method, and updates calculating parameter;3) calculate 2) in conversion coefficient observation vector, obtain its with 1) in observation vector residual error amount;4) repeat step 1)-the model that 3) is trained, and preservation model parameter;5) test observation data are input to the model trained with model parameter, image transform coefficients corresponding with test observation data are obtained;6) inverse transformation, the natural image finally rebuild are carried out to the conversion coefficient in 5).The natural image that the present invention is rebuild is clear, and reconstructed velocity is quickly, available for the recovery to natural image.
Description
Technical field
The invention belongs to image processing field, and in particular to a kind of natural image compressed sensing method for reconstructing, available for adopting
The natural image of sample recovers.
Background technology
With the development of medium technique, mass image data all suffers from huge challenge in terms of real-time Transmission, storage.
The proposition of compressed sensing technology causes these problems to open new thinking in theory, makes problem obtain effective solution.Pressure
Contracting perception theory thinks, if signal has openness under a certain kind conversion base, can carry out accidental projection sight to the signal
Survey, and Accurate Reconstruction is carried out to it by the prior information of signal with less observation, its model is to solve observation number
Norm optimization problem under being constrained according to fidelity.
For above-mentioned compressed sensing model, different norm constraints represents different restructing algorithms and reconstruction property.
According to norm, generally using the reconstruct of orthogonal matching pursuit OMP algorithms.Although norm meets compressed sensing model thinking initially
Method, that is, find the solution of the optimization problem with minimum degree of rarefication, but because it is a NP-Hard problem, causes the precision of solution
It is often not high.Therefore there is scholar to propose to substitute norm so that it becomes convex optimization problem using norm, and propose a series of be based on
The restructing algorithm of iteration:Iteration threshold contraction algorithm ISTA, iteratively faster threshold value contraction algorithm FISTA, approximate information transmission are calculated
Method AMP etc..Although the proposition of above-mentioned algorithm makes problem further be solved, but they are all based on the solution final accounts of optimum theory
Method, however it remains the problems such as reconstruct limited precision, iterative process are complicated, convergence rate is slow.
Recently as the development of depth learning technology, begin with scholar and propose the compressed sensing based on convolutional neural networks
Although reconstructing method Recon-Net, this method solves the problem of iterative process is complicated, but still suffers from two problems:1)
The reconstructed image noise that direct application model is obtained is larger, it is necessary to can just obtain the preferable reconstructed image of quality by denoising;2)
Model convergence rate in training is slower, and on high-performance computer, training pattern is also required to the time of one day.
The content of the invention
It is an object of the invention to for method for reconstructing of the tradition based on optimization and the reconstruction side for being currently based on deep learning
The problem of method is present, proposes a kind of natural image compressed sensing method for reconstructing based on depth sparse coding, multiple with simplified model
Miscellaneous degree, reduces the training time of model, improves the reconstructed velocity and quality reconstruction of image.
The technical scheme is that:It is pressed by using sparse prior information of the natural image on transform domain
Contracting perceptual coding, in conjunction with the approximate information pass-algorithm LAMP based on study and recurrent neural network RNN models, realizing will figure
As the restoration and reconstruction of coding information, implementation step includes as follows:
(1) model training step:
(1a) inputs plurality of pictures, and takes from these pictures n training image blocks X;
(1b) is compressed perception observation to n training image blocks X in (1a), obtains n observed differential Y, and use this
A little training image blocks constitute n training sample pair with corresponding observed differential:{ (X=x1,x2,...,xn-1,xn), (Y=y1,
y2,...,yn-1,yn)};
(1c) sets model training number of times K=100, randomly selects r training sample y from Y, X every timer、xr, and use
Gradient descent method is trained, and the cut-off condition flag trained every time is that 50 model error values of iteration are unattenuated;
(1d) sets the parameter of sparse coding algorithm, initializes iterations T=10, and make initial transformation systemSee
Survey data residual error vt=y, whereinFor the training image block conversion coefficient of the t times iterative calculation, vtFor the observation of the t times iteration
Residual error;
(1e) calculates the training image block conversion coefficient of the t+1 times iteration:WhereinFor
The conversion coefficient of the t times iteration, ATCtvtFor the conversion coefficient of the observation residual error of the t times iteration, ATIt is observing matrix A transposition,
CtIt is the t times parameter matrix to be optimized,For the threshold value of the t times iteration, αtIt is the scalar ginseng of the t times renewal
Numerical value, M is the dimension for observing data y, | | vt||2Represent vtTwo norms, ηst() is threshold value contracting function;
(1f) calculates the observation residual error of the t+1 times iteration:Wherein, bt+1vtIt is
Onsagercorrection;
(1g) circulation performs T (1e)-(1f) and obtains conversion coefficient
The conversion coefficient that (1h) is obtained as (1g)When meeting iteration cut-off condition flag, the model ginseng of this training is preserved
Number;
(1i) circulation performs K (1d)-(1h), completes model training;
(2) testing procedure:
(2a) will observe data ytestAnd the T parameter matrix obtained by model trainingWith scalar parameter valueIt is input in the model trained, obtains and input observation data ytestCorresponding test image conversion coefficient
(2b) is to conversion coefficientPCA inverse transformations are done, are obtained and observation data ytestCorresponding image Img:Wherein, Ψ-1Represent PCA inverse-transform matrixs;
(2c) converts the Ψ Ψ for possessing orthogonality and existing according to PCA-1=Ψ ΨTRelation, will be with observation data ytestIt is right
The image Img answered is rewritten as:Complete paired observations ytestNatural image rebuild, wherein, ΨTRepresent PCA
Direct transform matrix Ψ transposition.
The present invention has advantages below compared with other prior arts:
Firstth, present invention introduces the sparse prior information of natural image, with reference to the excellent of deep neural network and sparse coding
Gesture, reduces model complexity, so as to reduce the reconstruction time of image, realizes the quick reconstruction of compressed sensing, and carry
The high reconstruction effect of natural image;
Secondth, the present invention improves model training speed, so that implementation model using the model training method of transfer learning
Fast Training.
Brief description of the drawings
Fig. 1 realizes general flow chart for the present invention's;
Fig. 2 is the model training sub-process figure in the present invention;
Fig. 3 is the image reconstruction sub-process figure in the present invention;
Fig. 4 is Barbara primitive natures image used in emulation experiment of the present invention;
Fig. 5 is the reconstruction design sketch to Barbara images when compression ratio is 0.25 with existing TVAL3 methods;
Fig. 6 is the reconstruction design sketch to Barbara images when compression ratio is 0.25 with existing Recon-Net methods;
Fig. 7 is the reconstruction design sketch to Barbara images when compression ratio is 0.25 with the present invention.
Embodiment:
Embodiments of the invention and effect are described in detail below in conjunction with accompanying drawing:
Reference picture 1, the natural image method for reconstructing of the invention based on depth sparse coding, including model training and test two
Part.N training image blocks X is inputted first and training sample pair is constructed, and then carries out the model that model training is trained,
Test observation data input is tested into the model trained again, the natural image rebuild.
The model training of the present invention is described in detail with this two parts is tested below:
First, model training part
Reference picture 2, this part realizes that step is as follows:
Step 1:N training image blocks X is inputted, training sample pair is obtained,
(1a) inputs n training image blocks X, to the training image blocks data x of each inputiCarry out principal component analysis PCA
Conversion, obtains conversion coefficientWherein, Ψ represents principal component analysis PCA direct transform matrixes, according to principal component point
The orthogonality of PCA conversion is analysed, Ψ Ψ are obtained-1=Ψ ΨTRelational expression, drawn according to relational expressionWherein,
Ψ-1And ΨTPrincipal component analysis PCA inverse-transform matrixs and direct transform matrix Ψ transposition are represented respectively;
(1b) is observed according to compressed sensing observation model to each training image blocks, obtains observation data yi:Wherein, A=Φ ΨT, Φ is lack sampling gaussian random observing matrix, and vectorial w is the white Gaussian with zero-mean
Noise;
N training image blocks X is constituted n training sample pair by (1c) with corresponding n observed differential Y:{ (X=x1,
x2,...,xn-1,xn), (Y=y1,y2,...,yn-1,yn)}。
Step 2:Model training number of times is set, r training sample pair is randomly selected,
(2a) sets model training number of times K=100;
(2b) randomly selects r training sample to { x when training every time from Y, Xr,yr}。
Step 3:Correlated variables in the parameter of sparse coding algorithm, initialization algorithm is set.
(3a) initialization iterations T=10;
(3b) makes initial transform coefficientObserve data residual error vt=y, whereinFor the image of the t times iterative calculation
Block conversion coefficient, vtFor the observation residual error of the t times iteration.
Step 4:Calculate the training image block conversion coefficient of the t+1 times iteration
(4a) calculates the observation residual error v of the t times iterationtSparse coefficient ATCtvt, wherein ATIt is observing matrix A transposition,
CtIt is the t times parameter matrix to be optimized and is initialized as unit matrix;
(4b) calculates the training image blocks sparse coefficient of the t+1 times iteration,Wherein,For the t times
The conversion coefficient of iteration,For the threshold value of the t times iteration, αtIt is the scalar parameter value of the t times renewal, M is observation
Data y dimension, | | vt||2Represent vtTwo norms;
(4c) calculates the training image block conversion coefficient of the t+1 times iteration,
Wherein, ηst() is threshold value contracting function, for by threshold value λtWith sparse coefficient μt+1It is compared, specific method
It is that will be less than threshold value λtSparse coefficient μt+1Zero setting, will be greater than threshold value λtSparse coefficient μt+1It is set to μt+1With threshold value λtDifference
Absolute value.
Step 5:Calculate the observation residual error v of the t+1 times iterationt+1。
(5a) first obtains step 4In be more than zero coefficient and be set to 1, then it is averaged by row, obtained
Zero normWeight b is calculated againt+1:
Wherein N is conversion coefficientDimension, M is observation residual error vtDimension;
(5b) is by weight bt+1With observation residual error vtDot product is carried out, Onsager correction matrix b is obtainedt+1vt;
The matrix b that (5c) will be obtained in (5b)t+1vtSubstitute into formulaCalculate the t+1 times iteration
Observe residual error vt+1, wherein y is that training image blocks observe data, and A is observing matrix.
Step 6:Step 4-step 5 circulation is performed T=10 times, conversion coefficient is obtained
Step 7:Preserve the model parameter of this training.
The conversion coefficient obtained when step 6When meeting iteration cut-off condition flag, the model parameter of this training is preserved,
Wherein, the cut-off condition flag trained every time is that 50 model error values of iteration are unattenuated.
Step 8:Circulation performs K step 3-step 7, completes model training.
2nd, part of detecting
Reference picture 3, this part realizes that step is as follows:
Step 9:The parameter that data and model training part are preserved is observed in input test, obtains input observation data ytestIt is right
The image transform coefficients answered
T Matrix C of its preservation is taken out from model training parttAnd scalar cetIt is designated as respectivelyWithAnd will
The test observation data y collected in the two parameters and reality scenetestAs input, it is input in the model trained,
Output and observation data ytestCorresponding image transform coefficients
Step 10:Observation data y is obtained by principal component analysis PCA inverse transformationstestCorresponding natural image Img.
(10a) is to conversion coefficientPrincipal component analyzes PCA inverse transformations, obtains and observation data ytestCorresponding nature
Image:Wherein, Ψ-1Represent principal component analysis PCA inverse-transform matrixs;
The Ψ Ψ that (10b) is converted according to principal component analysis PCA-1=Ψ ΨTRelational expression, will be with observation data ytestIt is corresponding
Natural image Img is rewritten as:Complete paired observations ytestNatural image rebuild, wherein, ΨTRepresent master
Constituent analysis PCA direct transform matrixes Ψ transposition.
The effect of the present invention can be illustrated by following emulation experiment:
1st, simulated conditions:
1) programming platform used in emulation experiment is Pycharm v2016;
2) the natural image data used in emulation experiment come from standard exercise, test data set;
3) the training image block size used in emulation experiment is 25 × 25, and number of training n is 52650;
4) in emulation experiment, compressed sensing experimental result, Y-PSNR are evaluated using Y-PSNR PSNR indexs
PSNR is defined as:
Wherein, MAXiAnd MSEiTo rebuild high-resolution natural image Img out max pixel value and mean square error, N
For number of pixels.
2nd, emulation content:
Emulation 1, using TVAL3 methods, rebuilds, it is rebuild to natural image Barbara when compression ratio is 0.25
As a result it is as shown in Figure 5.
Emulation 2, using Recon-Net methods, rebuilds to natural image Barbara when compression ratio is 0.25, its
Reconstructed results are as shown in Figure 6.
Emulation 3, using the inventive method, rebuilds, it is rebuild to natural image Barbara when compression ratio is 0.25
As a result it is as shown in Figure 7.
The present invention, which is can be seen that, from the natural image Barbara reconstructed results shown in Fig. 5-Fig. 7 reconstructs next image
More apparent than the image that other method is reconstructed, image border is sharper keen, and visual effect is more preferable.
By existing TVAL3 methods, NLR-CS methods, Recon-Net methods and the inventive method respectively to natural image
Barbara carries out Reconstruction Simulation, obtained Y-PSNR PSNR, as shown in table 1..
The PSNR values of the different method for reconstructing of table 1
As it can be seen from table 1 the Y-PSNR PSNR of the present invention is 0.25 in compression ratio than existing TVAL3 methods
When high 3.73dB, to be higher by 2.00dB than existing Recon-Net.
Claims (3)
1. the natural image method for reconstructing based on depth sparse coding, including:
(1) model training step:
(1a) inputs plurality of pictures, and takes from these pictures n training image blocks X;
(1b) is compressed perception observation to n training image blocks X in (1a), obtains n observed differential Y, and instructed with these
Practice image block and constitute n training sample pair with corresponding observed differential:{ (X=x1,x2,...,xn-1,xn), (Y=y1,y2,...,
yn-1,yn)};
(1c) sets model training number of times K=100, randomly selects r training sample y from Y, X every timer、xr, and use gradient
Descent method is trained, and the cut-off condition flag trained every time is that 50 model error values of iteration are unattenuated;
(1d) sets the parameter of sparse coding algorithm, initializes iterations T=10, and make initial transformation systemObserve number
According to residual error vt=y, whereinFor the training image block conversion coefficient of the t times iterative calculation, vtFor the observation residual error of the t times iteration;
(1e) calculates the training image block conversion coefficient of the t+1 times iteration:WhereinFor t
The conversion coefficient of secondary iteration, ATCtvtFor the conversion coefficient of the observation residual error of the t times iteration, ATIt is observing matrix A transposition, CtIt is
The t times parameter matrix to be optimized,For the threshold value of the t times iteration, αtIt is the scalar parameter value of the t times renewal,
M is the dimension for observing data y, | | vt||2Represent vtTwo norms, ηst() is threshold value contracting function;
(1f) calculates the observation residual error of the t+1 times iteration:Wherein, bt+1vtIt is Onsager
Correction;
(1g) circulation performs T (1e)-(1f) and obtains conversion coefficient
The conversion coefficient that (1h) is obtained as (1g)When meeting iteration cut-off condition flag, the model parameter of this training is preserved;
(1i) circulation performs K (1d)-(1h), completes model training;
(2) testing procedure:
(2a) will observe data ytestAnd the T parameter matrix obtained by model trainingWith scalar parameter value
It is input in the model trained, obtains and input observation data ytestCorresponding test image conversion coefficient
(2b) is to conversion coefficientPCA inverse transformations are done, are obtained and observation data ytestCorresponding image Img:
Wherein, Ψ-1Represent PCA inverse-transform matrixs;
(2c) converts the Ψ Ψ for possessing orthogonality and existing according to PCA-1=Ψ ΨTRelation, will be with observation data ytestCorresponding figure
As Img is rewritten as:Complete paired observations ytestNatural image rebuild, wherein, ΨTRepresent PCA direct transforms
Matrix Ψ transposition.
2. perception in accordance with the method for claim 1, is compressed to n image block X in (1a) wherein in step (1b)
Observation, is carried out as follows:
(1b1) is to each image block data xiPCA conversion is carried out, conversion coefficient is obtained:Wherein, Ψ and Ψ-1Difference table
Show PCA direct transforms and its inverse transformation, simultaneously because the orthogonality of PCA conversion, meets Ψ Ψ-1=Ψ ΨT, then have,ΨTRepresent PCA direct transform matrixes Ψ transposition;
(1b2) is observed according to compressed sensing observation model to each image block, obtains observing data:Wherein
A=Φ ΨT, matrix Φ is lack sampling gaussian random observing matrix, and vectorial w is the white Gaussian noise with zero-mean.
3. according to the method described in claim (1), correction b of Onsager wherein in step (1f)t+1vt, press
Following steps are calculated:
(1f1) first willIn be more than zero coefficient and be set to 1, then it is averaged by row, obtainedZero normMost
Weight b is calculated afterwardst+1:
<mrow>
<msup>
<mi>b</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msup>
<mo>=</mo>
<mfrac>
<mi>N</mi>
<mi>M</mi>
</mfrac>
<mo>|</mo>
<mo>|</mo>
<msup>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msup>
<mo>|</mo>
<msub>
<mo>|</mo>
<mn>0</mn>
</msub>
<mo>,</mo>
</mrow>
Wherein, N is conversion coefficientDimension, M is observation residual error vtDimension;
(1f2) is by weight bt+1With observation residual error vtDot product is carried out, Onsager correction matrix b is obtainedt+1vt。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710306725.7A CN107154064B (en) | 2017-05-04 | 2017-05-04 | Natural image compressed sensing method for reconstructing based on depth sparse coding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710306725.7A CN107154064B (en) | 2017-05-04 | 2017-05-04 | Natural image compressed sensing method for reconstructing based on depth sparse coding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107154064A true CN107154064A (en) | 2017-09-12 |
CN107154064B CN107154064B (en) | 2019-07-23 |
Family
ID=59793689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710306725.7A Active CN107154064B (en) | 2017-05-04 | 2017-05-04 | Natural image compressed sensing method for reconstructing based on depth sparse coding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107154064B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610192A (en) * | 2017-09-30 | 2018-01-19 | 西安电子科技大学 | Adaptive observation compressed sensing image reconstructing method based on deep learning |
CN108629409A (en) * | 2018-04-28 | 2018-10-09 | 中国科学院计算技术研究所 | A kind of Processing with Neural Network system reducing IO expenses based on principal component analysis |
CN108629410A (en) * | 2018-04-28 | 2018-10-09 | 中国科学院计算技术研究所 | Based on principal component analysis dimensionality reduction and/or rise the Processing with Neural Network method tieed up |
CN110097497A (en) * | 2019-05-14 | 2019-08-06 | 电子科技大学 | Multi-scale image transformation and inverse transformation method based on residual multismoothlets |
CN110381313A (en) * | 2019-07-08 | 2019-10-25 | 东华大学 | Video compress sensing reconstructing method based on LSTM network Yu the blind assessment of image group quality |
CN110717949A (en) * | 2018-07-11 | 2020-01-21 | 天津工业大学 | Interference hyperspectral image sparse reconstruction based on TROMP |
CN113034414A (en) * | 2021-03-22 | 2021-06-25 | 上海交通大学 | Image reconstruction method, system, device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080028474A1 (en) * | 1999-07-29 | 2008-01-31 | Intertrust Technologies Corp. | Systems and Methods for Watermarking Software and Other Media |
CN102722896A (en) * | 2012-05-22 | 2012-10-10 | 西安电子科技大学 | Adaptive compressed sensing-based non-local reconstruction method for natural image |
CN105430416A (en) * | 2015-12-04 | 2016-03-23 | 四川大学 | Fingerprint image compression method based on adaptive sparse domain coding |
CN106530321A (en) * | 2016-10-28 | 2017-03-22 | 南方医科大学 | Multi-graph image segmentation based on direction and scale descriptors |
-
2017
- 2017-05-04 CN CN201710306725.7A patent/CN107154064B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080028474A1 (en) * | 1999-07-29 | 2008-01-31 | Intertrust Technologies Corp. | Systems and Methods for Watermarking Software and Other Media |
CN102722896A (en) * | 2012-05-22 | 2012-10-10 | 西安电子科技大学 | Adaptive compressed sensing-based non-local reconstruction method for natural image |
CN105430416A (en) * | 2015-12-04 | 2016-03-23 | 四川大学 | Fingerprint image compression method based on adaptive sparse domain coding |
CN106530321A (en) * | 2016-10-28 | 2017-03-22 | 南方医科大学 | Multi-graph image segmentation based on direction and scale descriptors |
Non-Patent Citations (1)
Title |
---|
王良君等: "多稀疏空间下的压缩感知图像重构", 《西安电子科技大学学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610192A (en) * | 2017-09-30 | 2018-01-19 | 西安电子科技大学 | Adaptive observation compressed sensing image reconstructing method based on deep learning |
CN107610192B (en) * | 2017-09-30 | 2021-02-12 | 西安电子科技大学 | Self-adaptive observation compressed sensing image reconstruction method based on deep learning |
CN108629409A (en) * | 2018-04-28 | 2018-10-09 | 中国科学院计算技术研究所 | A kind of Processing with Neural Network system reducing IO expenses based on principal component analysis |
CN108629410A (en) * | 2018-04-28 | 2018-10-09 | 中国科学院计算技术研究所 | Based on principal component analysis dimensionality reduction and/or rise the Processing with Neural Network method tieed up |
CN108629409B (en) * | 2018-04-28 | 2020-04-10 | 中国科学院计算技术研究所 | Neural network processing system for reducing IO overhead based on principal component analysis |
CN108629410B (en) * | 2018-04-28 | 2021-01-22 | 中国科学院计算技术研究所 | Neural network processing method based on principal component analysis dimension reduction and/or dimension increase |
CN110717949A (en) * | 2018-07-11 | 2020-01-21 | 天津工业大学 | Interference hyperspectral image sparse reconstruction based on TROMP |
CN110097497A (en) * | 2019-05-14 | 2019-08-06 | 电子科技大学 | Multi-scale image transformation and inverse transformation method based on residual multismoothlets |
CN110381313A (en) * | 2019-07-08 | 2019-10-25 | 东华大学 | Video compress sensing reconstructing method based on LSTM network Yu the blind assessment of image group quality |
CN110381313B (en) * | 2019-07-08 | 2021-08-31 | 东华大学 | Video compression sensing reconstruction method based on LSTM network and image group quality blind evaluation |
CN113034414A (en) * | 2021-03-22 | 2021-06-25 | 上海交通大学 | Image reconstruction method, system, device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107154064B (en) | 2019-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107154064A (en) | Natural image compressed sensing method for reconstructing based on depth sparse coding | |
CN109410261B (en) | Monocular image depth estimation method based on pyramid pooling module | |
CN111369487B (en) | Hyperspectral and multispectral image fusion method, system and medium | |
CN107133919A (en) | Time dimension video super-resolution method based on deep learning | |
CN106997581A (en) | A kind of method that utilization deep learning rebuilds high spectrum image | |
US20230419001A1 (en) | Three-dimensional fluid reverse modeling method based on physical perception | |
CN109241491A (en) | The structural missing fill method of tensor based on joint low-rank and rarefaction representation | |
CN110139046B (en) | Tensor-based video frame synthesis method | |
CN107133930A (en) | Ranks missing image fill method with rarefaction representation is rebuild based on low-rank matrix | |
CN104867119B (en) | The structural missing image fill method rebuild based on low-rank matrix | |
CN111080567A (en) | Remote sensing image fusion method and system based on multi-scale dynamic convolution neural network | |
CN108573479A (en) | The facial image deblurring and restoration methods of confrontation type network are generated based on antithesis | |
CN105118078B (en) | The CT image rebuilding methods of lack sampling | |
CN107784628A (en) | A kind of super-resolution implementation method based on reconstruction optimization and deep neural network | |
CN109102461B (en) | Image reconstruction method, device, equipment and medium for low-sampling block compressed sensing | |
CN105513033B (en) | A kind of super resolution ratio reconstruction method that non local joint sparse indicates | |
CN109523513A (en) | Based on the sparse stereo image quality evaluation method for rebuilding color fusion image | |
CN112465718A (en) | Two-stage image restoration method based on generation of countermeasure network | |
CN108734675A (en) | Image recovery method based on mixing sparse prior model | |
CN112257741B (en) | Method for detecting generative anti-false picture based on complex neural network | |
CN110378975B (en) | Compressed coding aperture imaging method and system based on deep neural network | |
CN107622515A (en) | The physical re-organization method of squeezed light field | |
CN108259893B (en) | Virtual reality video quality evaluation method based on double-current convolutional neural network | |
CN114418850A (en) | Super-resolution reconstruction method with reference image and fusion image convolution | |
CN112163998A (en) | Single-image super-resolution analysis method matched with natural degradation conditions |
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 |