Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets
Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well ad...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Institute of Electrical and Electronic Engineers
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/60242 |
| _version_ | 1848760590472839168 |
|---|---|
| author | Yang, L. Li, C. Han, J. Chen, C. Ye, Q. Zhang, B. Cao, X. Liu, Wan-Quan |
| author_facet | Yang, L. Li, C. Han, J. Chen, C. Ye, Q. Zhang, B. Cao, X. Liu, Wan-Quan |
| author_sort | Yang, L. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration. |
| first_indexed | 2025-11-14T10:18:12Z |
| format | Journal Article |
| id | curtin-20.500.11937-60242 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:18:12Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronic Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-602422018-07-06T02:00:40Z Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets Yang, L. Li, C. Han, J. Chen, C. Ye, Q. Zhang, B. Cao, X. Liu, Wan-Quan Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration. 2017 Journal Article http://hdl.handle.net/20.500.11937/60242 10.1109/JSTSP.2017.2743683 Institute of Electrical and Electronic Engineers restricted |
| spellingShingle | Yang, L. Li, C. Han, J. Chen, C. Ye, Q. Zhang, B. Cao, X. Liu, Wan-Quan Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title | Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title_full | Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title_fullStr | Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title_full_unstemmed | Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title_short | Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets |
| title_sort | image reconstruction via manifold constrained convolutional sparse coding for image sets |
| url | http://hdl.handle.net/20.500.11937/60242 |