Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer
Images corrupted by snowy adverse weather can impose performance impediments to critical high-level vision-based applications. Restoring snow-degraded images is vital, but the task is ill-posed and very challenging due to the veiling effect, stochastic distribution, and multi-scale characteristics o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10246273/ |
| _version_ | 1827813762446393344 |
|---|---|
| author | Obinna Agbodike Jenhui Chen |
| author_facet | Obinna Agbodike Jenhui Chen |
| author_sort | Obinna Agbodike |
| collection | DOAJ |
| description | Images corrupted by snowy adverse weather can impose performance impediments to critical high-level vision-based applications. Restoring snow-degraded images is vital, but the task is ill-posed and very challenging due to the veiling effect, stochastic distribution, and multi-scale characteristics of snow in a scene. In this regard, many existing image denoising methods are often less successful with respect to snow removal, being that they mostly achieve success with one snow dataset and underperform in others, thus questioning their robustness in tackling real-world complex snowfall scenarios. In this paper, we propose the wavelet in transformer (WiT) network to address the image desnow inverse problem. Our model exploits the joint systemic capabilities of the vision transformer and the renowned discrete wavelet transform to achieve effective restoration of snow-degraded images. In our experiments, we evaluated the performance of our model on the popular SRRS, SNOW100K, and CSD datasets, respectively. The efficacy of our learning-based network is proven by our obtained numeric and qualitative result outcomes indicating significant performance gains compared to image desnow benchmark models and other state-of-the-art methods in the literature. The source code is available at <uri>https://github.com/WINS-lab/WiT</uri>. |
| first_indexed | 2024-03-11T23:36:40Z |
| format | Article |
| id | doaj.art-2204eb65b01c4678aed786e47da2d854 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T23:36:40Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2204eb65b01c4678aed786e47da2d8542023-09-19T23:02:00ZengIEEEIEEE Access2169-35362023-01-0111994709948010.1109/ACCESS.2023.331394610246273Restoring Snow-Degraded Single Images With Wavelet in Vision TransformerObinna Agbodike0https://orcid.org/0000-0003-1297-952XJenhui Chen1https://orcid.org/0000-0002-8372-9221Department of Electrical Engineering, Chang Gung University, Taoyuan City, TaiwanDepartment of Computer Science and Information Engineering, Chang Gung University, Taoyuan City, TaiwanImages corrupted by snowy adverse weather can impose performance impediments to critical high-level vision-based applications. Restoring snow-degraded images is vital, but the task is ill-posed and very challenging due to the veiling effect, stochastic distribution, and multi-scale characteristics of snow in a scene. In this regard, many existing image denoising methods are often less successful with respect to snow removal, being that they mostly achieve success with one snow dataset and underperform in others, thus questioning their robustness in tackling real-world complex snowfall scenarios. In this paper, we propose the wavelet in transformer (WiT) network to address the image desnow inverse problem. Our model exploits the joint systemic capabilities of the vision transformer and the renowned discrete wavelet transform to achieve effective restoration of snow-degraded images. In our experiments, we evaluated the performance of our model on the popular SRRS, SNOW100K, and CSD datasets, respectively. The efficacy of our learning-based network is proven by our obtained numeric and qualitative result outcomes indicating significant performance gains compared to image desnow benchmark models and other state-of-the-art methods in the literature. The source code is available at <uri>https://github.com/WINS-lab/WiT</uri>.https://ieeexplore.ieee.org/document/10246273/Attentioncomputer-visiondesnowingtransformerwavelets |
| spellingShingle | Obinna Agbodike Jenhui Chen Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer IEEE Access Attention computer-vision desnowing transformer wavelets |
| title | Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer |
| title_full | Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer |
| title_fullStr | Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer |
| title_full_unstemmed | Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer |
| title_short | Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer |
| title_sort | restoring snow degraded single images with wavelet in vision transformer |
| topic | Attention computer-vision desnowing transformer wavelets |
| url | https://ieeexplore.ieee.org/document/10246273/ |
| work_keys_str_mv | AT obinnaagbodike restoringsnowdegradedsingleimageswithwaveletinvisiontransformer AT jenhuichen restoringsnowdegradedsingleimageswithwaveletinvisiontransformer |