Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908317608050688 |
|---|---|
| author | Wang, Yiwen Liang, Ying Zhang, Yuxuan Chai, Xinning Cheng, Zhengxue Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li |
| author_facet | Wang, Yiwen Liang, Ying Zhang, Yuxuan Chai, Xinning Cheng, Zhengxue Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li |
| contents | Due to the disparity between real-world degradations in user-generated content(UGC) images and synthetic degradations, traditional super-resolution methods struggle to generalize effectively, necessitating a more robust approach to model real-world distortions. In this paper, we propose a novel approach to UGC image super-resolution by integrating semantic guidance into a diffusion framework. Our method addresses the inconsistency between degradations in wild and synthetic datasets by separately simulating the degradation processes on the LSDIR dataset and combining them with the official paired training set. Furthermore, we enhance degradation removal and detail generation by incorporating a pretrained semantic extraction model (SAM2) and fine-tuning key hyperparameters for improved perceptual fidelity. Extensive experiments demonstrate the superiority of our approach against state-of-the-art methods. Additionally, the proposed model won second place in the CVPR NTIRE 2025 Short-form UGC Image Super-Resolution Challenge, further validating its effectiveness. The code is available at https://github.c10pom/Moonsofang/NTIRE-2025-SRlab. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09887 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution Wang, Yiwen Liang, Ying Zhang, Yuxuan Chai, Xinning Cheng, Zhengxue Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li Computer Vision and Pattern Recognition Due to the disparity between real-world degradations in user-generated content(UGC) images and synthetic degradations, traditional super-resolution methods struggle to generalize effectively, necessitating a more robust approach to model real-world distortions. In this paper, we propose a novel approach to UGC image super-resolution by integrating semantic guidance into a diffusion framework. Our method addresses the inconsistency between degradations in wild and synthetic datasets by separately simulating the degradation processes on the LSDIR dataset and combining them with the official paired training set. Furthermore, we enhance degradation removal and detail generation by incorporating a pretrained semantic extraction model (SAM2) and fine-tuning key hyperparameters for improved perceptual fidelity. Extensive experiments demonstrate the superiority of our approach against state-of-the-art methods. Additionally, the proposed model won second place in the CVPR NTIRE 2025 Short-form UGC Image Super-Resolution Challenge, further validating its effectiveness. The code is available at https://github.c10pom/Moonsofang/NTIRE-2025-SRlab. |
| title | Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.09887 |