Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models
Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data loss, which can significantly d...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587546847084544 |
|---|---|
| author | Shuo Li Mehrdad Yaghoobi |
| author_facet | Shuo Li Mehrdad Yaghoobi |
| author_sort | Shuo Li |
| collection | DOAJ |
| description | Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data loss, which can significantly degrade their quality and usefulness. This paper introduces a convergent guaranteed algorithm, LRS-PnP-DIP(1-Lip), which successfully addresses the instability issue of DHP that has been reported before. The proposed algorithm extends the successful joint low-rank and sparse model to further exploit the underlying data structures beyond the conventional and sometimes restrictive unions of subspace models. A stability analysis guarantees the convergence of the proposed algorithm under mild assumptions, which is crucial for its application in real-world scenarios. Extensive experiments demonstrate that the proposed solution consistently delivers visually and quantitatively superior inpainting results, establishing state-of-the-art performance. |
| format | Article |
| id | doaj-art-13bbefe4e3ff4391b6d3c06554bceab6 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-13bbefe4e3ff4391b6d3c06554bceab62025-01-24T13:48:00ZengMDPI AGRemote Sensing2072-42922025-01-0117228810.3390/rs17020288Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior ModelsShuo Li0Mehrdad Yaghoobi1School of Engineering, University of Edinburgh, Edinburgh EH8 9YL, UKInstitute of Imaging, Data and Communications, University of Edinburgh, Edinburgh EH8 9YL, UKHyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data loss, which can significantly degrade their quality and usefulness. This paper introduces a convergent guaranteed algorithm, LRS-PnP-DIP(1-Lip), which successfully addresses the instability issue of DHP that has been reported before. The proposed algorithm extends the successful joint low-rank and sparse model to further exploit the underlying data structures beyond the conventional and sometimes restrictive unions of subspace models. A stability analysis guarantees the convergence of the proposed algorithm under mild assumptions, which is crucial for its application in real-world scenarios. Extensive experiments demonstrate that the proposed solution consistently delivers visually and quantitatively superior inpainting results, establishing state-of-the-art performance.https://www.mdpi.com/2072-4292/17/2/288low ranksparsityhyperspectral image inpaintingself-supervised learningfixed-point convergence |
| spellingShingle | Shuo Li Mehrdad Yaghoobi Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models Remote Sensing low rank sparsity hyperspectral image inpainting self-supervised learning fixed-point convergence |
| title | Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models |
| title_full | Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models |
| title_fullStr | Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models |
| title_full_unstemmed | Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models |
| title_short | Self-Supervised Deep Hyperspectral Inpainting with Plug-and-Play and Deep Image Prior Models |
| title_sort | self supervised deep hyperspectral inpainting with plug and play and deep image prior models |
| topic | low rank sparsity hyperspectral image inpainting self-supervised learning fixed-point convergence |
| url | https://www.mdpi.com/2072-4292/17/2/288 |
| work_keys_str_mv | AT shuoli selfsuperviseddeephyperspectralinpaintingwithplugandplayanddeepimagepriormodels AT mehrdadyaghoobi selfsuperviseddeephyperspectralinpaintingwithplugandplayanddeepimagepriormodels |