Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.20302 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918069949956096 |
|---|---|
| author | Anwar, Abbas Shullar, Mohammad Nasir, Ali Arshad Masood, Mudassir Anwar, Saeed |
| author_facet | Anwar, Abbas Shullar, Mohammad Nasir, Ali Arshad Masood, Mudassir Anwar, Saeed |
| contents | Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in downstream tasks such as object detection, mapping, and classification. Our transformer-based diffusion model was developed to address image restoration tasks, aiming to improve the quality of degraded images. This model was evaluated against existing deep learning methodologies across multiple quality metrics for underwater image enhancement, denoising, and deraining on publicly available datasets. Our findings demonstrate that the diffusion model, combined with transformers, surpasses current methods in performance. The results of our model highlight the efficacy of diffusion models and transformers in improving the quality of degraded images, consequently expanding their utility in downstream tasks that require high-fidelity visual data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20302 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TDiR: Transformer based Diffusion for Image Restoration Tasks Anwar, Abbas Shullar, Mohammad Nasir, Ali Arshad Masood, Mudassir Anwar, Saeed Computer Vision and Pattern Recognition Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in downstream tasks such as object detection, mapping, and classification. Our transformer-based diffusion model was developed to address image restoration tasks, aiming to improve the quality of degraded images. This model was evaluated against existing deep learning methodologies across multiple quality metrics for underwater image enhancement, denoising, and deraining on publicly available datasets. Our findings demonstrate that the diffusion model, combined with transformers, surpasses current methods in performance. The results of our model highlight the efficacy of diffusion models and transformers in improving the quality of degraded images, consequently expanding their utility in downstream tasks that require high-fidelity visual data. |
| title | TDiR: Transformer based Diffusion for Image Restoration Tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.20302 |