{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:50Z","timestamp":1784268650205,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763863","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SeqTex: Generate Mesh Textures in Video Sequence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6673-9670","authenticated-orcid":false,"given":"Ze","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Hong Kong, Hong Kong City, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4531-1254","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong City, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6370-1603","authenticated-orcid":false,"given":"Yangtian","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong City, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6164-8343","authenticated-orcid":false,"given":"Yuan-Chen","family":"Guo","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-4374","authenticated-orcid":false,"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9774-4687","authenticated-orcid":false,"given":"Ding","family":"Liang","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-1626","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong City, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"2022. Renderpeople. https:\/\/renderpeople.com\/3d-people."},{"key":"e_1_3_3_2_3_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_4_1","unstructured":"Anthropic. 2024. Claude. https:\/\/claude.ai\/."},{"key":"e_1_3_3_2_5_1","unstructured":"Raphael Bensadoun Yanir Kleiman Idan Azuri Omri Harosh Andrea Vedaldi Natalia Neverova and Oran Gafni. 2024. Meta 3d texturegen: Fast and consistent texture generation for 3d objects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.02430 (2024)."},{"key":"e_1_3_3_2_6_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et\u00a0al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn. openai. com\/papers\/dall-e-3. pdf 2 3 (2023) 8."},{"key":"e_1_3_3_2_7_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. CoRR abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00819"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_3_2_10_1","unstructured":"Angel\u00a0X Chang Thomas Funkhouser Leonidas Guibas Pat Hanrahan Qixing Huang Zimo Li Silvio Savarese Manolis Savva Shuran Song Hao Su et\u00a0al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1512.03012 (2015)."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Boyuan Chen Diego Mart\u00ed\u00a0Mons\u00f3 Yilun Du Max Simchowitz Russ Tedrake and Vincent Sitzmann. 2024a. Diffusion forcing: Next-token prediction meets full-sequence diffusion. Advances in Neural Information Processing Systems 37 (2024) 24081\u201324125.","DOI":"10.52202\/079017-0759"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02018"},{"key":"e_1_3_3_2_15_1","unstructured":"Weifeng Chen Yatai Ji Jie Wu Hefeng Wu Pan Xie Jiashi Li Xin Xia Xuefeng Xiao and Liang Lin. 2023b. Control-a-video: Controllable text-to-video generation with diffusion models. arXiv e-prints (2023) arXiv\u20132305."},{"key":"e_1_3_3_2_16_1","unstructured":"Xi Chen Zhifei Zhang He Zhang Yuqian Zhou Soo\u00a0Ye Kim Qing Liu Yijun Li Jianming Zhang Nanxuan Zhao Yilin Wang et\u00a0al. 2024b. UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.07774 (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"An-Chieh Cheng Xueting Li Sifei Liu and Xiaolong Wang. 2023. TUVF: Learning Generalizable Texture UV Radiance Fields. CoRR abs\/2305.03040 (2023)."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Ruoshi Liu Matthew Wallingford Huong Ngo Oscar Michel Aditya Kusupati Alan Fan Christian Laforte Vikram Voleti Samir\u00a0Yitzhak Gadre et\u00a0al. 2023. Objaverse-xl: A universe of 10m+ 3d objects. Advances in Neural Information Processing Systems 36 (2023) 35799\u201335813.","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Zhao Dong Ka Chen Zhaoyang Lv Hong-Xing Yu Yunzhi Zhang Cheng Zhang Yufeng Zhu Stephen Tian Zhengqin Li Geordie Moffatt et\u00a0al. 2025. Digital twin catalog: A large-scale photorealistic 3d object digital twin dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.08541 (2025).","DOI":"10.1109\/CVPR52734.2025.00079"},{"key":"e_1_3_3_2_20_1","volume-title":"Forty-first international conference on machine learning","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et\u00a0al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_3_2_21_1","unstructured":"Yicong Hong Kai Zhang Jiuxiang Gu Sai Bi Yang Zhou Difan Liu Feng Liu Kalyan Sunkavalli Trung Bui and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.04400 (2023)."},{"key":"e_1_3_3_2_22_1","unstructured":"Wenbo Hu Xiangjun Gao Xiaoyu Li Sijie Zhao Xiaodong Cun Yong Zhang Long Quan and Ying Shan. 2024. Depthcrafter: Generating consistent long depth sequences for open-world videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02095 (2024)."},{"key":"e_1_3_3_2_23_1","unstructured":"Zehuan Huang Yuan-Chen Guo Haoran Wang Ran Yi Lizhuang Ma Yan-Pei Cao and Lu Sheng. 2024. Mv-adapter: Multi-view consistent image generation made easy. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03632 (2024)."},{"key":"e_1_3_3_2_24_1","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_2_25_1","unstructured":"Black\u00a0Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_3_2_26_1","unstructured":"Jiahao Li Hao Tan Kai Zhang Zexiang Xu Fujun Luan Yinghao Xu Yicong Hong Kalyan Sunkavalli Greg Shakhnarovich and Sai Bi. 2023. Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.06214 (2023)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_28_1","unstructured":"Shaoteng Liu Tianyu Wang Jui-Hsien Wang Qing Liu Zhifei Zhang Joon-Young Lee Yijun Li Bei Yu Zhe Lin Soo\u00a0Ye Kim et\u00a0al. 2024. Generative Video Propagation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19761 (2024)."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_2_30_1","unstructured":"Dustin Podell Zion English Kyle Lacey Andreas Blattmann Tim Dockhorn Jonas M\u00fcller Joe Penna and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.01952 (2023)."},{"key":"e_1_3_3_2_31_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_34_1","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Ruizhi Shao Yinghao Xu Yujun Shen Ceyuan Yang Yang Zheng Changan Chen Yebin Liu and Gordon Wetzstein. 2025. Interspatial Attention for Efficient 4D Human Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.15800 (2025).","DOI":"10.1145\/3731165"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Yawar Siddiqui Justus Thies Fangchang Ma Qi Shan Matthias Nie\u00dfner and Angela Dai. 2022. Texturify: Generating Textures on 3D Shape Surfaces. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.02411 (2022).","DOI":"10.1007\/978-3-031-20062-5_5"},{"key":"e_1_3_3_2_37_1","unstructured":"Dmitry Tochilkin David Pankratz Zexiang Liu Zixuan Huang Adam Letts Yangguang Li Ding Liang Christian Laforte Varun Jampani and Yan-Pei Cao. 2024. Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.02151 (2024)."},{"key":"e_1_3_3_2_38_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Voleti Vikram","year":"2024","unstructured":"Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitrii Tochilkin, Christian Laforte, Robin Rombach, and Varun Jampani. 2024. SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_39_1","unstructured":"Team Wan Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang et\u00a0al. 2025. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_2_40_1","unstructured":"Xiang Wang Hangjie Yuan Shiwei Zhang Dayou Chen Jiuniu Wang Yingya Zhang Yujun Shen Deli Zhao and Jingren Zhou. 2023b. Videocomposer: Compositional video synthesis with motion controllability. Advances in Neural Information Processing Systems 36 (2023) 7594\u20137611."},{"key":"e_1_3_3_2_41_1","unstructured":"Zhengyi Wang Cheng Lu Yikai Wang Fan Bao Chongxuan Li Hang Su and Jun Zhu. 2023a. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.16213 (2023)."},{"key":"e_1_3_3_2_42_1","unstructured":"Zeqi Xiao Yushi Lan Yifan Zhou Wenqi Ouyang Shuai Yang Yanhong Zeng and Xingang Pan. 2025. WORLDMEM: Long-term Consistent World Simulation with Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12369 (2025)."},{"key":"e_1_3_3_2_43_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"e_1_3_3_2_45_1","unstructured":"Mark YU Wenbo Hu Jinbo Xing and Ying Shan. 2025. TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.05638 (2025)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00388"},{"key":"e_1_3_3_2_48_1","unstructured":"Xin Yu Yuan-Chen Guo Yangguang Li Ding Liang Song-Hai Zhang and Xiaojuan Qi. 2023b. Text-to-3d with classifier score distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19415 (2023)."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Xin Yu Tianyu Wang Soo\u00a0Ye Kim Paul Guerrero Xi Chen Qing Liu Zhe Lin and Xiaojuan Qi. 2025. ObjectMover: Generative Object Movement with Video Prior. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.08037 (2025).","DOI":"10.1109\/CVPR52734.2025.01647"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"crossref","unstructured":"Xin Yu Ze Yuan Yuan-Chen Guo Ying-Tian Liu Jianhui Liu Yangguang Li Yan-Pei Cao Ding Liang and Xiaojuan Qi. 2024. Texgen: a generative diffusion model for mesh textures. ACM Transactions on Graphics (TOG) 43 6 (2024) 1\u201314.","DOI":"10.1145\/3687909"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"crossref","unstructured":"Qihang Zhang Shuangfei Zhai Miguel\u00a0Angel Bautista Kevin Miao Alexander Toshev Joshua Susskind and Jiatao Gu. 2024. World-consistent Video Diffusion with Explicit 3D Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.01821 (2024).","DOI":"10.1109\/CVPR52734.2025.02020"},{"key":"e_1_3_3_2_54_1","unstructured":"Zibo Zhao Zeqiang Lai Qingxiang Lin Yunfei Zhao Haolin Liu Shuhui Yang Yifei Feng Mingxin Yang Sheng Zhang Xianghui Yang et\u00a0al. 2025. Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12202 (2025)."},{"key":"e_1_3_3_2_55_1","unstructured":"Qi Zuo Xiaodong Gu Lingteng Qiu Yuan Dong Weihao Yuan Rui Peng Siyu Zhu Liefeng Bo Zilong Dong Qixing Huang et\u00a0al. 2024. Videomv: Consistent multi-view generation based on large video generative model. (2024)."}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:35:50Z","timestamp":1765251350000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":54,"alternative-id":["10.1145\/3757377.3763863","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763863","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}