{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:08Z","timestamp":1784228708658,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":71,"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":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM101"],"award-info":[{"award-number":["JYB2025XDXM101"]}]},{"name":"National Natural Science Foundation of China","award":["62495060"],"award-info":[{"award-number":["62495060"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811175","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":["Pixal3D: Pixel-Aligned 3D Generation from Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6938-3992","authenticated-orcid":false,"given":"Dong-Yang","family":"Li","sequence":"first","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8925-8574","authenticated-orcid":false,"given":"Wang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent ARC Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7854-1072","authenticated-orcid":false,"given":"Yuxin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent ARC Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6082-4966","authenticated-orcid":false,"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent ARC Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4128-4594","authenticated-orcid":false,"given":"Meng-Hao","family":"Guo","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8728-8726","authenticated-orcid":false,"given":"Fang-Lue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Victoria University of Wellington, Wellington, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent ARC Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7507-6542","authenticated-orcid":false,"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","unstructured":"Nicolas Carion Laura Gustafson Yuan-Ting Hu Shoubhik Debnath Ronghang Hu Didac Suris Chaitanya Ryali Kalyan\u00a0Vasudev Alwala Haitham Khedr Andrew Huang Jie Lei Tengyu Ma Baishan Guo Arpit Kalla Markus Marks Joseph Greer Meng Wang Peize Sun Roman R\u00e4dle Triantafyllos Afouras Effrosyni Mavroudi Katherine Xu Tsung-Han Wu Yu Zhou Liliane Momeni Rishi Hazra Shuangrui Ding Sagar Vaze Francois Porcher Feng Li Siyuan Li Aishwarya Kamath Ho\u00a0Kei Cheng Piotr Doll\u00e1r Nikhila Ravi Kate Saenko Pengchuan Zhang and Christoph Feichtenhofer. 2025. SAM 3: Segment Anything with Concepts. CoRR abs\/2511.16719 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.1671910.48550\/ARXIV.2511.16719","DOI":"10.48550\/ARXIV.2511.16719"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","unstructured":"Lo\u00efck Chambon Paul Couairon Eloi Zablocki Alexandre Boulch Nicolas Thome and Matthieu Cord. 2025. NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering. CoRR abs\/2511.18452 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.1845210.48550\/ARXIV.2511.18452","DOI":"10.48550\/ARXIV.2511.18452"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","unstructured":"Jiahao Chang Chongjie Ye Yushuang Wu Yuantao Chen Yidan Zhang Zhongjin Luo Chenghong Li Yihao Zhi and Xiaoguang Han. 2025. ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation. CoRR abs\/2510.23306 (2025). arXiv:https:\/\/arXiv.org\/abs\/2510.2330610.48550\/ARXIV.2510.23306","DOI":"10.48550\/ARXIV.2510.23306"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","unstructured":"Bardienus\u00a0Pieter Duisterhof Jan Oberst Bowen Wen Stan Birchfield Deva Ramanan and Jeffrey Ichnowski. 2025. RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion. CoRR abs\/2506.05285 (2025). arXiv:https:\/\/arXiv.org\/abs\/2506.0528510.48550\/ARXIV.2506.05285","DOI":"10.48550\/ARXIV.2506.05285"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","unstructured":"Xianglong He Zi-Xin Zou Chia-Hao Chen Yuan-Chen Guo Ding Liang Chun Yuan Wanli Ouyang Yan-Pei Cao and Yangguang Li. 2025. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling. CoRR abs\/2503.21732 (2025). arXiv:https:\/\/arXiv.org\/abs\/2503.2173210.48550\/ARXIV.2503.21732","DOI":"10.48550\/ARXIV.2503.21732"},{"key":"e_1_3_3_2_10_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Hong Yicong","year":"2024","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2024. LRM: Large Reconstruction Model for Single Image to 3D. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=sllU8vvsFF"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","unstructured":"Mu Hu Wei Yin Chi Zhang Zhipeng Cai Xiaoxiao Long Hao Chen Kaixuan Wang Gang Yu Chunhua Shen and Shaojie Shen. 2024. Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation. IEEE Trans. Pattern Anal. Mach. Intell. 46 12 (2024) 10579\u201310596. 10.1109\/TPAMI.2024.3444912","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","unstructured":"Binbin Huang Haobin Duan Yiqun Zhao Zibo Zhao Yi Ma and Shenghua Gao. 2025a. CUPID: Pose-Grounded Generative 3D Reconstruction from a Single Image. CoRR abs\/2510.20776 (2025). arXiv:https:\/\/arXiv.org\/abs\/2510.2077610.48550\/ARXIV.2510.20776","DOI":"10.48550\/ARXIV.2510.20776"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","unstructured":"Jiaxin Huang Yuanbo Yang Bangbang Yang Lin Ma Yuewen Ma and Yiyi Liao. 2025b. Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction. CoRR abs\/2601.04090 (2025). arXiv:https:\/\/arXiv.org\/abs\/2601.0409010.48550\/ARXIV.2601.04090","DOI":"10.48550\/ARXIV.2601.04090"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","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. CoRR abs\/2506.15442 (2025). arXiv:https:\/\/arXiv.org\/abs\/2506.1544210.48550\/ARXIV.2506.15442","DOI":"10.48550\/ARXIV.2506.15442"},{"key":"e_1_3_3_2_16_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","author":"Im Sunghoon","year":"2019","unstructured":"Sunghoon Im, Hae-Gon Jeon, Stephen Lin, and In\u00a0So Kweon. 2019. DPSNet: End-to-end Deep Plane Sweep Stereo. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=ryeYHi0ctQ"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","unstructured":"Tao Ju Frank Losasso Scott Schaefer and Joe\u00a0D. Warren. 2002. Dual contouring of hermite data. ACM Transactions on Graphics (TOG) 21 3 (2002) 339\u2013346. 10.1145\/566654.566586","DOI":"10.1145\/566654.566586"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","unstructured":"Zeqiang Lai Yunfei Zhao Zibo Zhao Haolin Liu Qingxiang Lin Jingwei Huang Chunchao Guo and Xiangyu Yue. 2025a. Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface. CoRR abs\/2512.03052 (2025). arXiv:https:\/\/arXiv.org\/abs\/2512.0305210.48550\/ARXIV.2512.03052","DOI":"10.48550\/ARXIV.2512.03052"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","unstructured":"Zeqiang Lai Yunfei Zhao Zibo Zhao Xin Yang Xin Huang Jingwei Huang Xiangyu Yue and Chunchao Guo. 2025b. NaTex: Seamless Texture Generation as Latent Color Diffusion. CoRR abs\/2511.16317 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.1631710.48550\/ARXIV.2511.16317","DOI":"10.48550\/ARXIV.2511.16317"},{"key":"e_1_3_3_2_21_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Lan Yushi","year":"2025","unstructured":"Yushi Lan, Shangchen Zhou, Zhaoyang Lyu, Fangzhou Hong, Shuai Yang, Bo Dai, Xingang Pan, and Chen\u00a0Change Loy. 2025. GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=P4DbTSDQFu"},{"key":"e_1_3_3_2_22_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Li Jiahao","year":"2024","unstructured":"Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, and Sai Bi. 2024. Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=2lDQLiH1W4"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","unstructured":"Rui Li Biao Zhang Zhenyu Li Federico Tombari and Peter Wonka. 2025d. LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning. CoRR abs\/2504.18424 (2025). arXiv:https:\/\/arXiv.org\/abs\/2504.1842410.48550\/ARXIV.2504.18424","DOI":"10.48550\/ARXIV.2504.18424"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730648"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","unstructured":"Yangguang Li Zi-Xin Zou Zexiang Liu Dehu Wang Yuan Liang Zhipeng Yu Xingchao Liu Yuan-Chen Guo Ding Liang Wanli Ouyang and Yan-Pei Cao. 2025e. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models. CoRR abs\/2502.06608 (2025). arXiv:https:\/\/arXiv.org\/abs\/2502.0660810.48550\/ARXIV.2502.06608","DOI":"10.48550\/ARXIV.2502.06608"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","unstructured":"Zhihao Li Yufei Wang Heliang Zheng Yihao Luo and Bihan Wen. 2025c. Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling. CoRR abs\/2505.14521 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.1452110.48550\/ARXIV.2505.14521","DOI":"10.48550\/ARXIV.2505.14521"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","unstructured":"Haotong Lin Sili Chen Junhao Liew Donny\u00a0Y. Chen Zhenyu Li Guang Shi Jiashi Feng and Bingyi Kang. 2025a. Depth Anything 3: Recovering the Visual Space from Any Views. CoRR abs\/2511.10647 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.1064710.48550\/ARXIV.2511.10647","DOI":"10.48550\/ARXIV.2511.10647"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","unstructured":"Yuchen Lin Chenguo Lin Panwang Pan Honglei Yan Yiqiang Feng Yadong Mu and Katerina Fragkiadaki. 2025b. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers. CoRR abs\/2506.05573 (2025). arXiv:https:\/\/arXiv.org\/abs\/2506.0557310.48550\/ARXIV.2506.05573","DOI":"10.48550\/ARXIV.2506.05573"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_31_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Liu Zhen","year":"2023","unstructured":"Zhen Liu, Yao Feng, Michael\u00a0J. Black, Derek Nowrouzezahrai, Liam Paull, and Weiyang Liu. 2023a. MeshDiffusion: Score-based Generative 3D Mesh Modeling. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=0cpM2ApF9p6"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","unstructured":"Yihao Luo Xianglong He Chuanyu Pan Yiwen Chen Jiaqi Wu Yangguang Li Wanli Ouyang Yuanming Hu Guang Yang and Choon\u00a0Hwai Yap. 2025. Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface. CoRR abs\/2511.04029 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.0402910.48550\/ARXIV.2511.04029","DOI":"10.48550\/ARXIV.2511.04029"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","unstructured":"Ming Meng Yonggui Zhu Yufei Zhao Zhaoxin Li and Zhe Zhu. 2025. 3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey. Computational Visual Media 11 3 (2025) 431\u2013464. 10.26599\/CVM.2025.9450438","DOI":"10.26599\/CVM.2025.9450438"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","unstructured":"Alex Nichol Heewoo Jun Prafulla Dhariwal Pamela Mishkin and Mark Chen. 2022. Point-E: A System for Generating 3D Point Clouds from Complex Prompts. CoRR abs\/2212.08751 (2022). arXiv:https:\/\/arXiv.org\/abs\/2212.0875110.48550\/ARXIV.2212.08751","DOI":"10.48550\/ARXIV.2212.08751"},{"key":"e_1_3_3_2_36_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy\u00a0V. Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Mido Assran Nicolas Ballas Wojciech Galuba Russell Howes Po-Yao Huang Shang-Wen Li Ishan Misra Michael Rabbat Vasu Sharma Gabriel Synnaeve Hu Xu Herv\u00e9 J\u00e9gou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"e_1_3_3_2_37_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 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, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","unstructured":"SAM Xingyu Chen Fu-Jen Chu Pierre Gleize Kevin\u00a0J. Liang Alexander Sax Hao Tang Weiyao Wang Michelle Guo Thibaut Hardin Xiang Li Aohan Lin Jiawei Liu Ziqi Ma Anushka Sagar Bowen Song Xiaodong Wang Jianing Yang Bowen Zhang Piotr Doll\u00e1r Georgia Gkioxari Matt Feiszli and Jitendra Malik. 2025. SAM 3D: 3Dfy Anything in Images. CoRR abs\/2511.16624 (2025). arXiv:https:\/\/arXiv.org\/abs\/2511.1662410.48550\/ARXIV.2511.16624","DOI":"10.48550\/ARXIV.2511.16624"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_3_3_2_41_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00184"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02304"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00498"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","unstructured":"Chen Wang Hao-Yang Peng Ying-Tian Liu Jiatao Gu and Shi-Min Hu. 2025b. Diffusion Models for 3D Generation: A Survey. Computational Visual Media 11 1 (2025) 1\u201328. 10.26599\/CVM.2025.9450452","DOI":"10.26599\/CVM.2025.9450452"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","unstructured":"Ruicheng Wang Sicheng Xu Yue Dong Yu Deng Jianfeng Xiang Zelong Lv Guangzhong Sun Xin Tong and Jiaolong Yang. 2025d. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details. CoRR abs\/2507.02546 (2025). arXiv:https:\/\/arXiv.org\/abs\/2507.0254610.48550\/ARXIV.2507.02546","DOI":"10.48550\/ARXIV.2507.02546"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Shengming Yin Shuai Bai Xiao Xu Yilei Chen Yuxiang Chen Zecheng Tang Zekai Zhang Zhengyi Wang An Yang Bowen Yu Chen Cheng Dayiheng Liu Deqing Li Hang Zhang Hao Meng Hu Wei Jingyuan Ni Kai Chen Kuan Cao Liang Peng Lin Qu Minggang Wu Peng Wang Shuting Yu Tingkun Wen Wensen Feng Xiaoxiao Xu Yi Wang Yichang Zhang Yongqiang Zhu Yujia Wu Yuxuan Cai and Zenan Liu. 2025a. Qwen-Image Technical Report. CoRR abs\/2508.02324 (2025). arXiv:https:\/\/arXiv.org\/abs\/2508.0232410.48550\/ARXIV.2508.02324","DOI":"10.48550\/ARXIV.2508.02324"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","unstructured":"Shuang Wu Youtian Lin Feihu Zhang Yifei Zeng Yikang Yang Yajie Bao Jiachen Qian Siyu Zhu Xun Cao Philip Torr and Yao Yao. 2025b. Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention. CoRR abs\/2505.17412 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.1741210.48550\/ARXIV.2505.17412","DOI":"10.48550\/ARXIV.2505.17412"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","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. 2025a. Native and Compact Structured Latents for 3D Generation. CoRR abs\/2512.14692 (2025). arXiv:https:\/\/arXiv.org\/abs\/2512.1469210.48550\/ARXIV.2512.14692","DOI":"10.48550\/ARXIV.2512.14692"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","unstructured":"Bojun Xiong Si-Tong Wei Xin-Yang Zheng Yan-Pei Cao Zhouhui Lian and Peng-Shuai Wang. 2025. OctFusion: Octree-based Diffusion Models for 3D Shape Generation. Comput. Graph. Forum 44 5 (2025). 10.1111\/CGF.70198","DOI":"10.1111\/CGF.70198"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","unstructured":"Yunhan Yang Yufan Zhou Yuan-Chen Guo Zi-Xin Zou Yukun Huang Ying-Tian Liu Hao Xu Ding Liang Yan-Pei Cao and Xihui Liu. 2025b. OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion. CoRR abs\/2507.06165 (2025). arXiv:https:\/\/arXiv.org\/abs\/2507.0616510.48550\/ARXIV.2507.06165","DOI":"10.48550\/ARXIV.2507.06165"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","unstructured":"Chongjie Ye Lingteng Qiu Xiaodong Gu Qi Zuo Yushuang Wu Zilong Dong Liefeng Bo Yuliang Xiu and Xiaoguang Han. 2024. StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal. ACM Transactions on Graphics (TOG) 43 6 (2024) 250:1\u2013250:18. 10.1145\/3687971","DOI":"10.1145\/3687971"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","unstructured":"Chongjie Ye Yushuang Wu Ziteng Lu Jiahao Chang Xiaoyang Guo Jiaqing Zhou Hao Zhao and Xiaoguang Han. 2025. Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging. CoRR abs\/2503.22236 (2025). arXiv:https:\/\/arXiv.org\/abs\/2503.2223610.48550\/ARXIV.2503.22236","DOI":"10.48550\/ARXIV.2503.22236"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","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) 213:1\u2013213:14. 10.1145\/3687909","DOI":"10.1145\/3687909"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","unstructured":"Biao Zhang Jiapeng Tang Matthias Nie\u00dfner and Peter Wonka. 2023. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models. ACM Transactions on Graphics (TOG) 42 4 (2023) 92:1\u201392:16. 10.1145\/3592442","DOI":"10.1145\/3592442"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","unstructured":"Longwen Zhang Ziyu Wang Qixuan Zhang Qiwei Qiu Anqi Pang Haoran Jiang Wei Yang Lan Xu and Jingyi Yu. 2024. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. ACM Transactions on Graphics (TOG) 43 4 (2024) 120:1\u2013120:20. 10.1145\/3658146","DOI":"10.1145\/3658146"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","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. CoRR abs\/2501.12202 (2025). arXiv:https:\/\/arXiv.org\/abs\/2501.1220210.48550\/ARXIV.2501.12202","DOI":"10.48550\/ARXIV.2501.12202"},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01861"},{"key":"e_1_3_3_2_72_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Zhou Junsheng","year":"2024","unstructured":"Junsheng Zhou, Jinsheng Wang, Baorui Ma, Yu-Shen Liu, Tiejun Huang, and Xinlong Wang. 2024. Uni3D: Exploring Unified 3D Representation at Scale. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=wcaE4Dfgt8"}],"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":"2026-07-16T18:17:19Z","timestamp":1784225839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811175"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":71,"alternative-id":["10.1145\/3799902.3811175","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811175","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"}}]}}