How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912944642588672 |
|---|---|
| author | Yin, Xiang Hu, Jinfan You, Zhiyuan Yan, Kainan Tang, Yu Dong, Chao Gu, Jinjin |
| author_facet | Yin, Xiang Hu, Jinfan You, Zhiyuan Yan, Kainan Tang, Yu Dong, Chao Gu, Jinjin |
| contents | Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new multi-dimensional evaluation pipeline that assesses models on detail, sharpness, semantic correctness, and overall quality. Our analysis covers diverse architectures, including diffusion-based, GAN-based, PSNR-oriented, and general-purpose generation models, revealing critical performance disparities. Furthermore, our analysis uncovers a key evolution in failure modes that signifies a paradigm shift for the perception-oriented low-level vision field. The central challenge is evolving from the previous problem of detail scarcity (under-generation) to the new frontier of detail quality and semantic control (preventing over-generation). We also leverage our benchmark to train a new IQA model that better aligns with human perceptual judgments. Ultimately, this work provides a systematic study of modern generative image restoration models, offering crucial insights that redefine our understanding of their true state and chart a course for future development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05010 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices Yin, Xiang Hu, Jinfan You, Zhiyuan Yan, Kainan Tang, Yu Dong, Chao Gu, Jinjin Computer Vision and Pattern Recognition Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new multi-dimensional evaluation pipeline that assesses models on detail, sharpness, semantic correctness, and overall quality. Our analysis covers diverse architectures, including diffusion-based, GAN-based, PSNR-oriented, and general-purpose generation models, revealing critical performance disparities. Furthermore, our analysis uncovers a key evolution in failure modes that signifies a paradigm shift for the perception-oriented low-level vision field. The central challenge is evolving from the previous problem of detail scarcity (under-generation) to the new frontier of detail quality and semantic control (preventing over-generation). We also leverage our benchmark to train a new IQA model that better aligns with human perceptual judgments. Ultimately, this work provides a systematic study of modern generative image restoration models, offering crucial insights that redefine our understanding of their true state and chart a course for future development. |
| title | How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.05010 |