Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.22710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912455799603200 |
|---|---|
| author | Yuan, Jiang Ma, JI Wang, Bo Ke, Guanzhou Hu, Weiming |
| author_facet | Yuan, Jiang Ma, JI Wang, Bo Ke, Guanzhou Hu, Weiming |
| contents | Implicit degradation estimation-based blind super-resolution (IDE-BSR) hinges on extracting the implicit degradation representation (IDR) of the LR image and adapting it to LR image features to guide HR detail restoration. Although IDE-BSR has shown potential in dealing with noise interference and complex degradations, existing methods ignore the importance of IDR discriminability for BSR and instead over-complicate the adaptation process to improve effect, resulting in a significant increase in the model's parameters and computations. In this paper, we focus on the discriminability optimization of IDR and propose a new powerful and lightweight BSR model termed LightBSR. Specifically, we employ a knowledge distillation-based learning framework. We first introduce a well-designed degradation-prior-constrained contrastive learning technique during teacher stage to make the model more focused on distinguishing different degradation types. Then we utilize a feature alignment technique to transfer the degradation-related knowledge acquired by the teacher to the student for practical inferencing. Extensive experiments demonstrate the effectiveness of IDR discriminability-driven BSR model design. The proposed LightBSR can achieve outstanding performance with minimal complexity across a range of blind SR tasks. Our code is accessible at: https://github.com/MJ-NCEPU/LightBSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning Yuan, Jiang Ma, JI Wang, Bo Ke, Guanzhou Hu, Weiming Computer Vision and Pattern Recognition Image and Video Processing Implicit degradation estimation-based blind super-resolution (IDE-BSR) hinges on extracting the implicit degradation representation (IDR) of the LR image and adapting it to LR image features to guide HR detail restoration. Although IDE-BSR has shown potential in dealing with noise interference and complex degradations, existing methods ignore the importance of IDR discriminability for BSR and instead over-complicate the adaptation process to improve effect, resulting in a significant increase in the model's parameters and computations. In this paper, we focus on the discriminability optimization of IDR and propose a new powerful and lightweight BSR model termed LightBSR. Specifically, we employ a knowledge distillation-based learning framework. We first introduce a well-designed degradation-prior-constrained contrastive learning technique during teacher stage to make the model more focused on distinguishing different degradation types. Then we utilize a feature alignment technique to transfer the degradation-related knowledge acquired by the teacher to the student for practical inferencing. Extensive experiments demonstrate the effectiveness of IDR discriminability-driven BSR model design. The proposed LightBSR can achieve outstanding performance with minimal complexity across a range of blind SR tasks. Our code is accessible at: https://github.com/MJ-NCEPU/LightBSR. |
| title | LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2506.22710 |