{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:18Z","timestamp":1765309278957,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"National Science Foundation of China","award":["62125201"],"award-info":[{"award-number":["62125201"]}]},{"name":"National Science Foundation of China","award":["U24B20174"],"award-info":[{"award-number":["U24B20174"]}]},{"name":"National Science Foundation of China","award":["62102381"],"award-info":[{"award-number":["62102381"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754903","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"9454-9462","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DiffusionMat: Alpha Matting as Deterministic Sequential Refinement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3383-4349","authenticated-orcid":false,"given":"Yangyang","family":"Xu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4104-1373","authenticated-orcid":false,"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1864-8326","authenticated-orcid":false,"given":"Yong","family":"Du","sequence":"additional","affiliation":[{"name":"Ocean University of China, Tsingtao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8560-9007","authenticated-orcid":false,"given":"Kwan-Yee K.","family":"Wong","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tunc Ozan Aydin, and Marc Pollefeys","author":"Aksoy Yagiz","year":"2017","unstructured":"Yagiz Aksoy, Tunc Ozan Aydin, and Marc Pollefeys. 2017. Designing effective inter-pixel information flow for natural image matting. In CVPR. 29--37."},{"key":"e_1_3_2_1_2_1","volume-title":"Segdiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390","author":"Amit Tomer","year":"2021","unstructured":"Tomer Amit, Tal Shaharbany, Eliya Nachmani, and LiorWolf. 2021. Segdiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)."},{"key":"e_1_3_2_1_3_1","unstructured":"Jacob Austin Daniel D Johnson Jonathan Ho Daniel Tarlow and Rianne van den Berg. 2021. Structured denoising diffusion models in discrete state-spaces. In NeurIPS. 17981--17993."},{"key":"e_1_3_2_1_4_1","unstructured":"Dmitry Baranchuk Ivan Rubachev Andrey Voynov Valentin Khrulkov and Artem Babenko. 2022. Label-efficient semantic segmentation with diffusion models. In ICLR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Huanqia Cai Fanglei Xue Lele Xu and Lili Guo. 2022. TransMatting: Enhancing Transparent Objects Matting with Transformers. In ECCV. 253--269.","DOI":"10.1007\/978-3-031-19818-2_15"},{"key":"e_1_3_2_1_6_1","unstructured":"Shaofan Cai Xiaoshuai Zhang Haoqiang Fan Haibin Huang Jiangyu Liu Jiaming Liu Jiaying Liu Jue Wang and Jian Sun. 2019. Disentangled Image Matting. In ICCV. 8819--8828."},{"key":"e_1_3_2_1_7_1","volume-title":"ECCV Workshop. 205--218","author":"Cao Hu","year":"2022","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2022. Swin-unet: Unet-like pure transformer for medical image segmentation. In ECCV Workshop. 205--218."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.18"},{"key":"e_1_3_2_1_10_1","volume-title":"Diffusiondet: Diffusion model for object detection. In ICCV. 19830--19843.","author":"Chen Shoufa","year":"2023","unstructured":"Shoufa Chen, Peize Sun, Yibing Song, and Ping Luo. 2023. Diffusiondet: Diffusion model for object detection. In ICCV. 19830--19843."},{"key":"e_1_3_2_1_11_1","volume-title":"Fleet","author":"Chen Ting","year":"2023","unstructured":"Ting Chen, Lala Li, Saurabh Saxena, Geoffrey Hinton, and David J. Fleet. 2023. A Generalist Framework for Panoptic Segmentation of Images and Videos. In ICCV. 909--919."},{"key":"e_1_3_2_1_12_1","unstructured":"Ting Chen Ruixiang Zhang and Geoffrey Hinton. 2023. Analog bits: Generating discrete data using diffusion models with self-conditioning. In ICLR."},{"key":"e_1_3_2_1_13_1","unstructured":"Yung-Yu Chuang Brian Curless David H Salesin and Richard Szeliski. 2001. A bayesian approach to digital matting. In CVPR. II--II."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Junjie Deng Yangyang Xu Zeyang Zhou and Shengfeng He. 2022. Background matting via recursive excitation. In ICME. 1--6.","DOI":"10.1109\/ICME52920.2022.9859876"},{"key":"e_1_3_2_1_15_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. In NeurIPS. 8780--8794."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Ben Fei Zhaoyang Lyu Liang Pan Junzhe Zhang Weidong Yang Tianyue Luo Bo Zhang and Bo Dai. 2023. Generative Diffusion Prior for Unified Image Restoration and Enhancement. In CVPR. 9935--9946.","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"e_1_3_2_1_17_1","unstructured":"Shuyang Gu Dong Chen Jianmin Bao FangWen Bo Zhang Dongdong Chen Lu Yuan and Baining Guo. 2022. Vector quantized diffusion model for text-to-image synthesis. In CVPR. 10696--10706."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Kaiming He Christoph Rhemann Carsten Rother Xiaoou Tang and Jian Sun. 2011. A global sampling method for alpha matting. In CVPR. 2049--2056.","DOI":"10.1109\/CVPR.2011.5995495"},{"key":"e_1_3_2_1_19_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Yihan Hu Yiheng Lin Wei Wang Yao Zhao Yunchao Wei and Humphrey Shi. 2024. Diffusion for natural image matting. In ECCV. 181--199.","DOI":"10.1007\/978-3-031-72998-0_11"},{"key":"e_1_3_2_1_21_1","volume-title":"Ddp: Diffusion model for dense visual prediction. In ICCV. 21741--21752.","author":"Ji Yuanfeng","year":"2023","unstructured":"Yuanfeng Ji, Zhe Chen, Enze Xie, Lanqing Hong, Xihui Liu, Zhaoqiang Liu, Tong Lu, Zhenguo Li, and Ping Luo. 2023. Ddp: Diffusion model for dense visual prediction. In ICCV. 21741--21752."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Boah Kim Yujin Oh and Jong Chul Ye. 2023. Diffusion adversarial representation learning for self-supervised vessel segmentation. In ICLR.","DOI":"10.1016\/j.media.2023.103022"},{"key":"e_1_3_2_1_23_1","unstructured":"Diederik Kingma Tim Salimans Ben Poole and Jonathan Ho. 2021. Variational diffusion models. In NeurIPS. 21696--21707."},{"key":"e_1_3_2_1_24_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1177"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.168"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Jizhizi Li Sihan Ma Jing Zhang and Dacheng Tao. 2021. Privacy-preserving portrait matting. In ACM Multimedia. 3501--3509.","DOI":"10.1145\/3474085.3475512"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yaoyi Li and Hongtao Lu. 2020. Natural Image Matting via Guided Contextual Attention. In AAAI. 11450--11457.","DOI":"10.1609\/aaai.v34i07.6809"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yuhao Liu Jiake Xie Xiao Shi Yu Qiao Yujie Huang Yong Tang and Xin Yang. 2021. Tripartite information mining and integration for image matting. In ICCV. 7555--7564.","DOI":"10.1109\/ICCV48922.2021.00746"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Hao Lu Yutong Dai Chunhua Shen and Songcen Xu. 2019. Indices matter: Learning to index for deep image matting. In ICCV. 3266--3275.","DOI":"10.1109\/ICCV.2019.00336"},{"key":"e_1_3_2_1_31_1","volume-title":"Alphagan: Generative adversarial networks for natural image matting. In BMVC.","author":"Lutz Sebastian","year":"2018","unstructured":"Sebastian Lutz, Konstantinos Amplianitis, and Aljosa Smolic. 2018. Alphagan: Generative adversarial networks for natural image matting. In BMVC."},{"key":"e_1_3_2_1_32_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. In ICLR.","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, JiajunWu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. In ICLR."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Ron Mokady Amir Hertz Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2023. Null-text inversion for editing real images using guided diffusion models. In CVPR. 6038--6047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_34_1","volume-title":"Matteformer: Transformer-based image matting via prior-tokens. In CVPR. 11696--11706.","author":"Park GyuTae","year":"2022","unstructured":"GyuTae Park, SungJoon Son, JaeYoung Yoo, SeHo Kim, and Nojun Kwak. 2022. Matteformer: Transformer-based image matting via prior-tokens. In CVPR. 11696--11706."},{"key":"e_1_3_2_1_35_1","volume-title":"Fatezero: Fusing attentions for zero-shot text-based video editing. In ICCV. 15932--15942.","author":"Qi Chenyang","year":"2023","unstructured":"Chenyang Qi, Xiaodong Cun, Yong Zhang, Chenyang Lei, Xintao Wang, Ying Shan, and Qifeng Chen. 2023. Fatezero: Fusing attentions for zero-shot text-based video editing. In ICCV. 15932--15942."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yu Qiao Yuhao Liu Xin Yang Dongsheng Zhou Mingliang Xu Qiang Zhang and Xiaopeng Wei. 2020. Attention-guided hierarchical structure aggregation for image matting. In CVPR. 13676--13685.","DOI":"10.1109\/CVPR42600.2020.01369"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Christoph Rhemann Carsten Rother JueWang Margrit Gelautz Pushmeet Kohli and Pamela Rott. 2009. A perceptually motivated online benchmark for image matting. In CVPR. 1826--1833.","DOI":"10.1109\/CVPR.2009.5206503"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR. 10684--10695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_39_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In MICCAI. 234--241.","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI. 234--241."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Ehsan Shahrian Deepu Rajan Brian Price and Scott Cohen. 2013. Improving image matting using comprehensive sampling sets. In CVPR. 636--643.","DOI":"10.1109\/CVPR.2013.88"},{"key":"e_1_3_2_1_41_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In ICLR."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Jingwei Tang Yagiz Aksoy Cengiz \u00d6ztireli Markus Gross and Tun\u00e7 Ozan Aydin. 2019. Learning-based Sampling for Natural Image Matting. In CVPR.","DOI":"10.1109\/CVPR.2019.00317"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Jue Wang and Michael F Cohen. 2007. Optimized color sampling for robust matting. In CVPR. 1--8.","DOI":"10.1109\/CVPR.2007.383006"},{"key":"e_1_3_2_1_44_1","unstructured":"Ning Xu Brian Price Scott Cohen and Thomas Huang. 2017. Deep image matting. In CVPR. 2970--2979."},{"key":"e_1_3_2_1_45_1","first-page":"5332","article-title":"Self-supervised mattingspecific portrait enhancement and generation","volume":"31","author":"Xu Yangyang","year":"2022","unstructured":"Yangyang Xu, Zeyang Zhou, and Shengfeng He. 2022. Self-supervised mattingspecific portrait enhancement and generation. IEEE TIP 31 (2022), 5332--5342.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Shuai Yang Yifan Zhou Ziwei Liu and Chen Change Loy. 2023. Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation. In SIGGRAPH ASIA.","DOI":"10.1145\/3610548.3618160"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3408323","article-title":"Smart scribbles for image matting","volume":"16","author":"Yang Xin","year":"2020","unstructured":"Xin Yang, Yu Qiao, Shaozhe Chen, Shengfeng He, Baocai Yin, Qiang Zhang, Xiaopeng Wei, and Rynson WH Lau. 2020. Smart scribbles for image matting. ACM Transactions on Multimedia Computing, Communications and Applications 16, 4 (2020), 1--21.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_48_1","volume-title":"Baocai Yin Yin, and Rynson Lau","author":"Yang Xin","year":"2018","unstructured":"Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin Yin, and Rynson Lau. 2018. Active matting. In NeurIPS. 4590--4600."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Qihang Yu Jianming Zhang He Zhang Yilin Wang Zhe Lin Ning Xu Yutong Bai and Alan Yuille. 2021. Mask guided matting via progressive refinement network. In CVPR. 1154--1163.","DOI":"10.1109\/CVPR46437.2021.00121"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. In ICCV. 3836--3847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Wenliang Zhao Yongming Rao Zuyan Liu Benlin Liu Jie Zhou and Jiwen Lu. 2023. Unleashing Text-to-Image Diffusion Models for Visual Perception. In ICCV. 5729--5739.","DOI":"10.1109\/ICCV51070.2023.00527"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:38:13Z","timestamp":1765309093000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754903"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3754903","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754903","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}