IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models
Solving total variation problems is fundamentally important for many computer vision tasks, such as image smoothing, optical flow estimation and 3D surface reconstruction. However, the traditional iterative solvers require a large number of iterations to converge, while deep learning solvers have a...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838572/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592934756679680 |
|---|---|
| author | Yuanhao Gong |
| author_facet | Yuanhao Gong |
| author_sort | Yuanhao Gong |
| collection | DOAJ |
| description | Solving total variation problems is fundamentally important for many computer vision tasks, such as image smoothing, optical flow estimation and 3D surface reconstruction. However, the traditional iterative solvers require a large number of iterations to converge, while deep learning solvers have a huge number of parameters, hampering their practical deployment. To address these issues, this paper first introduces a novel iterative algorithm that is 6 ~ 75 times faster than previous iterative methods. The proposed iterative method converges and converges to the optimal solution. These two facts are theoretically guaranteed and numerically confirmed, respectively. Then, we generalize this algorithm to a compact implicit neural network that has only 0.003M parameters. The network is shown to be more effective and efficient. Thanks to the small number of parameters, the proposed network can be applied in a wide range of applications where total variation is imposed. The source code for the iterative solver and the neural network is publicly available at <uri>https://github.com/gyh8/IRS</uri>. |
| format | Article |
| id | doaj-art-7aefe6f81fef4fa5ad82cd0f648e94c9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7aefe6f81fef4fa5ad82cd0f648e94c92025-01-21T00:01:48ZengIEEEIEEE Access2169-35362025-01-0113102891029810.1109/ACCESS.2025.352863710838572IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation ModelsYuanhao Gong0https://orcid.org/0000-0001-5702-1927College of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaSolving total variation problems is fundamentally important for many computer vision tasks, such as image smoothing, optical flow estimation and 3D surface reconstruction. However, the traditional iterative solvers require a large number of iterations to converge, while deep learning solvers have a huge number of parameters, hampering their practical deployment. To address these issues, this paper first introduces a novel iterative algorithm that is 6 ~ 75 times faster than previous iterative methods. The proposed iterative method converges and converges to the optimal solution. These two facts are theoretically guaranteed and numerically confirmed, respectively. Then, we generalize this algorithm to a compact implicit neural network that has only 0.003M parameters. The network is shown to be more effective and efficient. Thanks to the small number of parameters, the proposed network can be applied in a wide range of applications where total variation is imposed. The source code for the iterative solver and the neural network is publicly available at <uri>https://github.com/gyh8/IRS</uri>.https://ieeexplore.ieee.org/document/10838572/Neural networkresidual solvertotal variationunfold |
| spellingShingle | Yuanhao Gong IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models IEEE Access Neural network residual solver total variation unfold |
| title | IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models |
| title_full | IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models |
| title_fullStr | IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models |
| title_full_unstemmed | IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models |
| title_short | IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models |
| title_sort | irsnet an implicit residual solver and its unfolding neural network with 0 003m parameters for total variation models |
| topic | Neural network residual solver total variation unfold |
| url | https://ieeexplore.ieee.org/document/10838572/ |
| work_keys_str_mv | AT yuanhaogong irsnetanimplicitresidualsolveranditsunfoldingneuralnetworkwith0003mparametersfortotalvariationmodels |