{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:30Z","timestamp":1784228730181,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811065","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8919-7984","authenticated-orcid":false,"given":"Yihong","family":"Guo","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6723-3517","authenticated-orcid":false,"given":"Youwei","family":"Lyu","sequence":"additional","affiliation":[{"name":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0254-9764","authenticated-orcid":false,"given":"Jiajun","family":"Tang","sequence":"additional","affiliation":[{"name":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1334-8235","authenticated-orcid":false,"given":"Yizhuo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hanghzou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2977-2852","authenticated-orcid":false,"given":"Hongliang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8954-0873","authenticated-orcid":false,"given":"Jinwei","family":"Chen","sequence":"additional","affiliation":[{"name":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8264-6849","authenticated-orcid":false,"given":"Changqing","family":"Zou","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China and Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1249-2826","authenticated-orcid":false,"given":"Qingnan","family":"Fan","sequence":"additional","affiliation":[{"name":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_4_1","volume-title":"The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition","author":"Bychkovsky Vladimir","year":"2011","unstructured":"Vladimir Bychkovsky, Sylvain Paris, Eric Chan, and Fr\u00e9do Durand. 2011. Learning Photographic Global Tonal Adjustment with a Database of Input \/ Output Image Pairs. In The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093321"},{"key":"e_1_3_3_2_6_1","unstructured":"Haoyu Chen Keda Tao Yizao Wang Xinlei Wang Lei Zhu and Jinjin Gu. 2025. PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23130 (2025)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00660"},{"key":"e_1_3_3_2_8_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et\u00a0al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.06261 (2025)."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240531"},{"key":"e_1_3_3_2_10_1","unstructured":"Keyan Ding Kede Ma Shiqi Wang and Eero\u00a0P Simoncelli. 2020. Image quality assessment: Unifying structure and texture similarity. IEEE transactions on pattern analysis and machine intelligence 44 5 (2020) 2567\u20132581."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681130"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Niladri\u00a0Shekhar Dutt Duygu Ceylan and Niloy\u00a0J Mitra. 2025. MonetGPT: Solving Puzzles Enhances MLLMs\u2019 Image Retouching Skills. ACM Transactions on Graphics (TOG) 44 4 (2025) 1\u201312.","DOI":"10.1145\/3730926"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Micha\u00ebl Gharbi Jiawen Chen Jonathan\u00a0T Barron Samuel\u00a0W Hasinoff and Fr\u00e9do Durand. 2017. Deep bilateral learning for real-time image enhancement. ACM Transactions on Graphics (TOG) 36 4 (2017) 1\u201312.","DOI":"10.1145\/3072959.3073592"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Yuanming Hu Hao He Chenxi Xu Baoyuan Wang and Stephen Lin. 2018. Exposure: A white-box photo post-processing framework. ACM Transactions on Graphics (TOG) 37 2 (2018) 1\u201317.","DOI":"10.1145\/3181974"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00442"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_23"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_21"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6790"},{"key":"e_1_3_3_2_20_1","unstructured":"Black\u00a0Forest Labs Stephen Batifol Andreas Blattmann Frederic Boesel Saksham Consul Cyril Diagne Tim Dockhorn Jack English Zion English Patrick Esser et\u00a0al. 2025. FLUX. 1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.15742 (2025)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00071"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25248"},{"key":"e_1_3_3_2_23_1","unstructured":"Yunlong Lin Zixu Lin Kunjie Lin Jinbin Bai Panwang Pan Chenxin Li Haoyu Chen Zhongdao Wang Xinghao Ding Wenbo Li et\u00a0al. 2025. JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.17612 (2025)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01284"},{"key":"e_1_3_3_2_25_1","unstructured":"Temesgen Muruts\u00a0Weldengus Binnan Liu Fei Kou Youwei Lyu Jinwei Chen Qingnan Fan and Changqing Zou. 2025. InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning Using an Asymmetric Auto-Encoder. arXiv e-prints (2025) arXiv\u20132602."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01117"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Zhaoqing Pan Feng Yuan Jianjun Lei Wanqing Li Nam Ling and Sam Kwong. 2021. MIEGAN: Mobile image enhancement via a multi-module cascade neural network. IEEE Transactions on Multimedia 24 (2021) 519\u2013533.","DOI":"10.1109\/TMM.2021.3054509"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00621"},{"key":"e_1_3_3_2_29_1","unstructured":"Christoph Schuhmann and Romain Beaumont. 2022. LAION-AESTHETICS. Technical report and blog post. https:\/\/laion.ai\/blog\/laion-aesthetics\/"},{"key":"e_1_3_3_2_30_1","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont Robert Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes Jenia Jitsev and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.02114 (2021)."},{"key":"e_1_3_3_2_31_1","first-page":"92","volume-title":"European Conference on Computer Vision","author":"Serrano-Lozano David","year":"2024","unstructured":"David Serrano-Lozano, Luis Herranz, Michael\u00a0S Brown, and Javier Vazquez-Corral. 2024. NamedCurves: Learned Image Enhancement via Color Naming. In European Conference on Computer Vision. Springer, 92\u2013108."},{"key":"e_1_3_3_2_32_1","unstructured":"Unsplash. 2024. Unsplash Dataset. https:\/\/unsplash.com\/data. Accessed: 2025-06-20."},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01841"},{"key":"e_1_3_3_2_34_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Sheng-ming Yin Shuai Bai Xiao Xu Yilei Chen et\u00a0al. 2025. Qwen-image technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.02324 (2025)."},{"key":"e_1_3_3_2_35_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Liang Liao Chunyi Li Yixuan Gao Annan Wang Erli Zhang Wenxiu Sun et\u00a0al. 2023. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17090 (2023)."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Wufeng Xue Lei Zhang Xuanqin Mou and Alan\u00a0C Bovik. 2013. Gradient magnitude similarity deviation: A highly efficient perceptual image quality index. IEEE transactions on image processing 23 2 (2013) 684\u2013695.","DOI":"10.1109\/TIP.2013.2293423"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01700"},{"key":"e_1_3_3_2_38_1","first-page":"144","volume-title":"European Conference on Computer Vision","author":"Yang Sidi","year":"2024","unstructured":"Sidi Yang, Binxiao Huang, Mingdeng Cao, Yatai Ji, Hanzhong Guo, Ngai Wong, and Yujiu Yang. 2024. Taming Lookup Tables for Efficient Image Retouching. In European Conference on Computer Vision. Springer, 144\u2013159."},{"key":"e_1_3_3_2_39_1","unstructured":"Qiying Yu Zheng Zhang Ruofei Zhu Yufeng Yuan Xiaochen Zuo Yu Yue Weinan Dai Tiantian Fan Gaohong Liu Lingjun Liu et\u00a0al. 2025. Dapo: An open-source llm reinforcement learning system at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.14476 (2025)."},{"key":"e_1_3_3_2_40_1","unstructured":"Runsheng Yu Wenyu Liu Yasen Zhang Zhi Qu Deli Zhao and Bo Zhang. 2018. Deepexposure: Learning to expose photos with asynchronously reinforced adversarial learning. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Hui Zeng Jianrui Cai Lida Li Zisheng Cao and Lei Zhang. 2020. Learning image-adaptive 3d lookup tables for high performance photo enhancement in real-time. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 4 (2020) 2058\u20132073.","DOI":"10.1109\/TPAMI.2020.3026740"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Kai Zhang Lingbo Mo Wenhu Chen Huan Sun and Yu Su. 2023a. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems 36 (2023) 31428\u201331449.","DOI":"10.52202\/075280-1365"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:19:16Z","timestamp":1784225956000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":42,"alternative-id":["10.1145\/3799902.3811065","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811065","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}