RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910980660789248 |
|---|---|
| author | Conde, Marcos V. Timofte, Radu Berdan, Radu Besbinar, Beril Iso, Daisuke Ji, Pengzhou Dun, Xiong Fan, Zeying Wu, Chen Wang, Zhansheng Zhang, Pengbo Huang, Jiazi Liu, Qinglin Yu, Wei Zhang, Shengping Ji, Xiangyang Kim, Kyungsik Kim, Minkyung Lee, Hwalmin Ma, Hekun Zheng, Huan Wei, Yanyan Zhang, Zhao Fang, Jing Gao, Meilin Yu, Xiang Xie, Shangbin Sun, Mengyuan Yue, Huanjing Cheng, Jingyu Yang Huize Zhang, Shaomeng Zhang, Zhaoyang Liang, Haoxiang |
| author_facet | Conde, Marcos V. Timofte, Radu Berdan, Radu Besbinar, Beril Iso, Daisuke Ji, Pengzhou Dun, Xiong Fan, Zeying Wu, Chen Wang, Zhansheng Zhang, Pengbo Huang, Jiazi Liu, Qinglin Yu, Wei Zhang, Shengping Ji, Xiangyang Kim, Kyungsik Kim, Minkyung Lee, Hwalmin Ma, Hekun Zheng, Huan Wei, Yanyan Zhang, Zhao Fang, Jing Gao, Meilin Yu, Xiang Xie, Shangbin Sun, Mengyuan Yue, Huanjing Cheng, Jingyu Yang Huize Zhang, Shaomeng Zhang, Zhaoyang Liang, Haoxiang |
| contents | Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report Conde, Marcos V. Timofte, Radu Berdan, Radu Besbinar, Beril Iso, Daisuke Ji, Pengzhou Dun, Xiong Fan, Zeying Wu, Chen Wang, Zhansheng Zhang, Pengbo Huang, Jiazi Liu, Qinglin Yu, Wei Zhang, Shengping Ji, Xiangyang Kim, Kyungsik Kim, Minkyung Lee, Hwalmin Ma, Hekun Zheng, Huan Wei, Yanyan Zhang, Zhao Fang, Jing Gao, Meilin Yu, Xiang Xie, Shangbin Sun, Mengyuan Yue, Huanjing Cheng, Jingyu Yang Huize Zhang, Shaomeng Zhang, Zhaoyang Liang, Haoxiang Image and Video Processing Computer Vision and Pattern Recognition Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data. |
| title | RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.01947 |