{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:35Z","timestamp":1784228795130,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":84,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U25A20440"],"award-info":[{"award-number":["U25A20440"]}]},{"name":"National Natural Science Foundation of China","award":["62472373"],"award-info":[{"award-number":["62472373"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811120","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":["PixTex: Consistent 3D Texturing via Pixel-Space Multi-View Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8512-0551","authenticated-orcid":false,"given":"Yuqing","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang, Hangzhou, 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\/0000-0001-5690-367X","authenticated-orcid":false,"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2432-809X","authenticated-orcid":false,"given":"Yiqian","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4968-7306","authenticated-orcid":false,"given":"Sirui","family":"Lin","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6575-2931","authenticated-orcid":false,"given":"Yuqing","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, 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\/0000-0001-6164-8343","authenticated-orcid":false,"given":"Yuan-Chen","family":"Guo","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-2920","authenticated-orcid":false,"given":"Xiaogang","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China and State Key Laboratory of CAD&CG, Zhejiang University, 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":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine et\u00a0al. 2022. Ediff-i: Text-to-image Diffusion Models with An Ensemble of Expert Denoisers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.01324 (2022)."},{"key":"e_1_3_3_2_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_3_2_5_1","unstructured":"Chia-Hao Chen Zi-Xin Zou Yan-Pei Cao Ze Yuan Guan Luo Xiaojuan Qi Ding Liang Song-Hai Zhang and Yuan-Chen Guo. 2025c. LaFiTe: A Generative Latent Field for 3D Native Texturing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.04786 (2025)."},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_8_1","unstructured":"Shoufa Chen Chongjian Ge Shilong Zhang Peize Sun and Ping Luo. 2025a. PixelFlow: Pixel-Space Generative Models with Flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.07963 (2025)."},{"key":"e_1_3_3_2_9_1","unstructured":"Zhennan Chen Junwei Zhu Xu Chen Jiangning Zhang Xiaobin Hu Hanzhen Zhao Chengjie Wang Jian Yang and Ying Tai. 2025b. DiP: Taming Diffusion Models in Pixel Space. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.18822 (2025)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Wei Cheng Juncheng Mu Xianfang Zeng Xin Chen Anqi Pang Chi Zhang Zhibin Wang Bin Fu Gang Yu Ziwei Liu et\u00a0al. 2024. MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.02336 (2024).","DOI":"10.1109\/CVPR52734.2025.00063"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"e_1_3_3_2_12_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models Beat Gans on Image Synthesis. Advances in Neural Information Processing Systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_3_2_13_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","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, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024."},{"key":"e_1_3_3_2_14_1","unstructured":"Jiashi Feng Xiu Li Jing Lin Jiahang Liu Gaohong Liu Weiqiang Lou Su Ma Guang Shi Qinlong Wang Jun Wang Zhongcong Xu Xuanyu Yi Zihao Yu Jianfeng Zhang Yifan Zhu Rui Chen Jinxin Chi Zixian Du Li Han Lixin Huang Kaihua Jiang Yuhan Li Guan Luo Shuguang Wang Qianyi Wu Fan Yang Junyang Zhang and Xuanmeng Zhang. 2025a. Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.19944 (2025)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Yifei Feng Mingxin Yang Shuhui Yang Sheng Zhang Jiaao Yu Zibo Zhao Yuhong Liu Jie Jiang and Chunchao Guo. 2025b. RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.19011 (2025).","DOI":"10.1109\/ICCV51701.2025.01598"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00442"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1595"},{"key":"e_1_3_3_2_18_1","unstructured":"Zebin He Mingxin Yang Shuhui Yang Yixuan Tang Tao Wang Kaihao Zhang Guanying Chen Yuhong Liu Jie Jiang Chunchao Guo and Wenhan Luo. 2025. MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10289 (2025)."},{"key":"e_1_3_3_2_19_1","volume-title":"Annual Conference on Neural Information Processing Systems 2017, NeurIPS 2017","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Annual Conference on Neural Information Processing Systems 2017, NeurIPS 2017."},{"key":"e_1_3_3_2_20_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free Diffusion Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.12598 (2022)."},{"key":"e_1_3_3_2_21_1","first-page":"13213","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Hoogeboom Emiel","year":"2023","unstructured":"Emiel Hoogeboom, Jonathan Heek, and Tim Salimans. 2023. Simple Diffusion: End-to-End Diffusion for High Resolution Images. In International Conference on Machine Learning, ICML 2023. 13213\u201313232."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Emiel Hoogeboom Thomas Mensink Jonathan Heek Kay Lamerigts Ruiqi Gao and Tim Salimans. 2024. Simpler Diffusion (sid2): 1.5 Fid on Imagenet512 with Pixel-space Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.19324 (2024).","DOI":"10.1109\/CVPR52734.2025.01683"},{"key":"e_1_3_3_2_23_1","unstructured":"Xin Huang Tengfei Wang Ziwei Liu and Qing Wang. 2024. Material Anything: Generating Materials for Any 3D Object via Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15138 (2024)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01520"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00062"},{"key":"e_1_3_3_2_26_1","unstructured":"Hunyuan3D. 2026. Hunyuan3D Studio. https:\/\/3d.hunyuan.tencent.com\/studio"},{"key":"e_1_3_3_2_27_1","unstructured":"Team Hunyuan3D Shuhui Yang Mingxin Yang Yifei Feng Xin Huang Sheng Zhang Zebin He Di Luo Haolin Liu Yunfei Zhao Qingxiang Lin Zeqiang Lai Xianghui Yang Huiwen Shi Zibo Zhao Bowen Zhang Hongyu Yan Lifu Wang Sicong Liu Jihong Zhang Meng Chen Liang Dong Yiwen Jia Yulin Cai Jiaao Yu Yixuan Tang Dongyuan Guo Junlin Yu Hao Zhang Zheng Ye Peng He Runzhou Wu Shida Wei Chao Zhang Yonghao Tan Yifu Sun Lin Niu Shirui Huang Bojian Zheng Shu Liu Shilin Chen Xiang Yuan Xiaofeng Yang Kai Liu Jianchen Zhu Peng Chen Tian Liu Di Wang Yuhong Liu Linus Jie Jiang Jingwei Huang and Chunchao Guo. 2025. Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.15442 (2025)."},{"key":"e_1_3_3_2_28_1","unstructured":"Allan Jabri David Fleet and Ting Chen. 2022. Scalable Adaptive Computation for Iterative Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.11972 (2022)."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"e_1_3_3_2_30_1","unstructured":"DaDong Jiang Xianghui Yang Zibo Zhao Sheng Zhang Jiaao Yu Zeqiang Lai Shaoxiong Yang Chunchao Guo Xiaobo Zhou and Zhihui Ke. 2024. Flexitex: Enhancing texture generation with visual guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12431 (2024)."},{"key":"e_1_3_3_2_31_1","unstructured":"Yang Jin Zhicheng Sun Ningyuan Li Kun Xu Hao Jiang Nan Zhuang Quzhe Huang Yang Song Yadong Mu and Zhouchen Lin. 2024. Pyramidal Flow Matching for Efficient Video Generative Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.05954 (2024)."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"e_1_3_3_2_33_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding Variational Bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_2_34_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_35_1","unstructured":"Zeqiang Lai Yunfei Zhao Zibo Zhao Xin Yang Xin Huang Jingwei Huang Xiangyu Yue and Chunchao Guo. 2025. NaTex: Seamless Texture Generation as Latent Color Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.16317 (2025)."},{"key":"e_1_3_3_2_36_1","unstructured":"Biwen Lei Yang Li Xinhai Liu Shuhui Yang Lixin Xu Jingwei Huang Ruining Tang Haohan Weng Jian Liu Jing Xu et\u00a0al. 2025. Hunyuan3d Studio: End-to-End Ai Pipeline for Game-ready 3D Asset Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.12815 (2025)."},{"key":"e_1_3_3_2_37_1","unstructured":"Hui Li Baoyou Chen Liwei Zhang Jiaye Li Jingdong Wang and Siyu Zhu. 2025a. Pyramidal Patchification Flow for Visual Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.23543 (2025)."},{"key":"e_1_3_3_2_38_1","unstructured":"Tianhong Li and Kaiming He. 2025. Back to Basics: Let Denoising Generative Models Denoise. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.13720 (2025)."},{"key":"e_1_3_3_2_39_1","unstructured":"Tianhong Li Qinyi Sun Lijie Fan and Kaiming He. 2025b. Fractal generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.17437 (2025)."},{"key":"e_1_3_3_2_40_1","unstructured":"Weiyu Li Xuanyang Zhang Zheng Sun Di Qi Hao Li Wei Cheng Weiwei Cai Shihao Wu Jiarui Liu Zihao Wang Xiao Chen Feipeng Tian Jianxiong Pan Zeming Li Gang Yu Xiangyu Zhang Daxin Jiang and Ping Tan. 2025c. Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.07747 (2025)."},{"key":"e_1_3_3_2_41_1","unstructured":"Yixun Liang Kunming Luo Xiao Chen Rui Chen Hongyu Yan Weiyu Li Jiarui Liu and Ping Tan. 2025. UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23253 (2025)."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02474"},{"key":"e_1_3_3_2_43_1","unstructured":"Xingchao Liu Chengyue Gong and Qiang Liu. 2022. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.03003 (2022)."},{"key":"e_1_3_3_2_44_1","unstructured":"Yuxin Liu Minshan Xie Hanyuan Liu and Tien-Tsin Wong. 2023. Text-Guided Texturing by Synchronized Multi-View Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.12891 (2023)."},{"key":"e_1_3_3_2_45_1","unstructured":"Jiawei Lu Yingpeng Zhang Zengjun Zhao He Wang Kun Zhou and Tianjia Shao. 2024. GenesisTex2: Stable Consistent and High-Quality Text-to-Texture Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.18401 (2024)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00760"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70180"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Sai Raj\u00a0Kishore Perla Yizhi Wang Ali Mahdavi-Amiri and Hao Zhang. 2024. EASI-Tex: Edge-Aware Mesh Texturing from Single Image. ACM Trans. Graph. 43 4 (2024) 40:1\u201340:11.","DOI":"10.1145\/3658222"},{"key":"e_1_3_3_2_50_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_51_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_3_2_52_1","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021. 8748\u20138763."},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily Denton Seyed Kamyar\u00a0Seyed Ghasemipour Burcu\u00a0Karagol Ayan S\u00a0Sara Mahdavi Rapha\u00a0Gontijo Lopes et\u00a0al. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.11487 (2022).","DOI":"10.52202\/068431-2643"},{"key":"e_1_3_3_2_56_1","unstructured":"Mingqi Shao Feng Xiong Zhaoxu Sun and Mu Xu. 2025. MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.12635 (2025)."},{"key":"e_1_3_3_2_57_1","unstructured":"Alex Shonenkov Misha Konstantinov Daria Bakshandaeva Christoph Schuhmann Ksenia Ivanova and Nadiia Klokova. 2023. DeepFloyd-if. https:\/\/github.com\/deep-floyd\/IF."},{"key":"e_1_3_3_2_58_1","first-page":"2256","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015","volume":"37","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric\u00a0A. Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015 , Vol.\u00a037. 2256\u20132265."},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"crossref","unstructured":"Jianlin Su Murtadha H.\u00a0M. Ahmed Yu Lu Shengfeng Pan Wen Bo and Yunfeng Liu. 2024. RoFormer: Enhanced Transformer with Rotary Position Embedding. Neurocomputing 568 (2024) 127063.","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687547"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00597"},{"key":"e_1_3_3_2_62_1","unstructured":"Jiayan Teng Wendi Zheng Ming Ding Wenyi Hong Jianqiao Wangni Zhuoyi Yang and Jie Tang. 2023. Relay Diffusion: Unifying Diffusion Process across Resolutions for Image Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.03350 (2023)."},{"key":"e_1_3_3_2_63_1","unstructured":"VAST. 2026. Tripo Studio - Your next 3D workspace with AI. https:\/\/studio.tripo3d.ai\/"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687386"},{"key":"e_1_3_3_2_65_1","unstructured":"Shuai Wang Ziteng Gao Chenhui Zhu Weilin Huang and Limin Wang. 2025. Pixnerd: Pixel neural field diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.23268 (2025)."},{"key":"e_1_3_3_2_66_1","unstructured":"Jinbo Wu Xing Liu Chenming Wu Xiaobo Gao Jialun Liu Xinqi Liu Chen Zhao Haocheng Feng Errui Ding and Jingdong Wang. 2024. TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.15009 (2024)."},{"key":"e_1_3_3_2_67_1","unstructured":"Jianfeng Xiang Xiaoxue Chen Sicheng Xu Ruicheng Wang Zelong Lv Yu Deng Hongyuan Zhu Yue Dong Hao Zhao Nicholas\u00a0Jing Yuan and Jiaolong Yang. 2025. Native and Compact Structured Latents for 3D Generation. Tech report (2025)."},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"crossref","unstructured":"Jianfeng Xiang Zelong Lv Sicheng Xu Yu Deng Ruicheng Wang Bowen Zhang Dong Chen Xin Tong and Jiaolong Yang. 2024. Structured 3D Latents for Scalable and Versatile 3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.01506 (2024).","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"crossref","unstructured":"Zhiyu Xie Yuqing Zhang Xiangjun Tang Yiqian Wu Dehan Chen Gongsheng Li and Xiaogang Jin. 2024. StyleTex: Style Image-Guided Texture Generation for 3D Models. ACM Trans. Graph. 43 6 (2024) 212:1\u2013212:14.","DOI":"10.1145\/3687931"},{"key":"e_1_3_3_2_70_1","unstructured":"Yu-Ying Yeh Jia-Bin Huang Changil Kim Lei Xiao Thu Nguyen-Phuoc Numair Khan Cheng Zhang Manmohan Chandraker Carl\u00a0S Marshall Zhao Dong et\u00a0al. 2024. TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.09416 (2024)."},{"key":"e_1_3_3_2_71_1","unstructured":"Kim Youwang Tae-Hyun Oh and Gerard Pons-Moll. 2023. Paint-It: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11360 (2023)."},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00388"},{"key":"e_1_3_3_2_73_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 Trans. Graph. 43 6 (2024) 213:1\u2013213:14.","DOI":"10.1145\/3687909"},{"key":"e_1_3_3_2_74_1","unstructured":"Yongsheng Yu Wei Xiong Weili Nie Yichen Sheng Shiqiu Liu and Jiebo Luo. 2025. PixelDiT: Pixel Diffusion Transformers for Image Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.20645 (2025)."},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"crossref","unstructured":"Ze Yuan Xin Yu Yangtian Sun Yuan-Chen Guo Yan-Pei Cao Ding Liang and Xiaojuan Qi. 2025. SeqTex: Generate Mesh Textures in Video Sequence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.04285 (2025).","DOI":"10.1145\/3757377.3763863"},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"crossref","unstructured":"Xianfang Zeng Xin Chen Zhongqi Qi Wen Liu Zibo Zhao Zhibin Wang Bin Fu Yong Liu and Gang Yu. 2023. Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.13913 (2023).","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"e_1_3_3_2_77_1","unstructured":"Shuangfei Zhai Ruixiang Zhang Preetum Nakkiran David Berthelot Jiatao Gu Huangjie Zheng Tianrong Chen Miguel\u00a0Angel Bautista Navdeep Jaitly and Josh Susskind. 2024. Normalizing Flows are Capable Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.06329 (2024)."},{"key":"e_1_3_3_2_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687637"},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657494"},{"key":"e_1_3_3_2_80_1","doi-asserted-by":"crossref","unstructured":"Longwen Zhang Ziyu Wang Qixuan Zhang Qiwei Qiu Anqi Pang Haoran Jiang Wei Yang Lan Xu and Jingyi Yu. 2024e. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. ACM Trans. Graph. 43 4 (2024) 120:1\u2013120:20.","DOI":"10.1145\/3658146"},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657504"},{"key":"e_1_3_3_2_83_1","doi-asserted-by":"crossref","unstructured":"Yuqing Zhang Yuan Liu Zhiyu Xie Lei Yang Zhongyuan Liu Mengzhou Yang Runze Zhang Qilong Kou Cheng Lin Wenping Wang and Xiaogang Jin. 2024a. DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models. ACM Trans. Graph. 43 4 (2024) 39:1\u201339:18.","DOI":"10.1145\/3658170"},{"key":"e_1_3_3_2_84_1","doi-asserted-by":"crossref","unstructured":"Yuqing Zhang Hao Xu Yiqian Wu Sirui Chen Sirui Lin Xiang Li Xifeng Gao and Xiaogang Jin. 2025. AlignTex: Pixel-Precise Texture Generation from Multi-view Artwork. ACM Trans. Graph. 44 4 (2025) 161:1\u2013161:12.","DOI":"10.1145\/3731158"},{"key":"e_1_3_3_2_85_1","unstructured":"Zibo Zhao Zeqiang Lai Qingxiang Lin Yunfei Zhao Haolin Liu Shuhui Yang Yifei Feng Mingxin Yang Sheng Zhang Xianghui Yang Huiwen Shi Sicong Liu Junta Wu Yihang Lian Fan Yang Ruining Tang Zebin He Xinzhou Wang Jian Liu Xuhui Zuo Zhuo Chen Biwen Lei Haohan Weng Jing Xu Yiling Zhu Xinhai Liu Lixin Xu Changrong Hu Tianyu Huang Lifu Wang Jihong Zhang Meng Chen Liang Dong Yiwen Jia Yulin Cai Jiaao Yu Yixuan Tang Hao Zhang Zheng Ye Peng He Runzhou Wu Chao Zhang Yonghao Tan Jie Xiao Yangyu Tao Jianchen Zhu Jinbao Xue Kai Liu Chongqing Zhao Xinming Wu Zhichao Hu Lei Qin Jianbing Peng Zhan Li Minghui Chen Xipeng Zhang Lin Niu Paige Wang Yingkai Wang Haozhao Kuang Zhongyi Fan Xu Zheng Weihao Zhuang YingPing He Tian Liu Yong Yang Di Wang Yuhong Liu Jie Jiang Jingwei Huang and Chunchao Guo. 2025. Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12202 (2025)."}],"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":"2026-07-16T18:26:55Z","timestamp":1784226415000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":84,"alternative-id":["10.1145\/3799902.3811120","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811120","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"}}]}}