{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:08Z","timestamp":1784228768143,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":57,"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\/3799902.3811117","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":["CubePart: An Open-Vocabulary Part-Controllable 3D Generator"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8169-2218","authenticated-orcid":false,"given":"Yiheng","family":"Zhu","sequence":"first","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0565-4255","authenticated-orcid":false,"given":"Kangle","family":"Deng","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3784-1451","authenticated-orcid":false,"given":"Jean-Philippe","family":"Fauconnier","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8763-4134","authenticated-orcid":false,"given":"Inaki","family":"Navarro","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8479-3380","authenticated-orcid":false,"given":"Daiqing","family":"Li","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4148-3164","authenticated-orcid":false,"given":"Ava","family":"Pun","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA and Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8523-891X","authenticated-orcid":false,"given":"Yinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5149-6461","authenticated-orcid":false,"given":"Peiye","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0369-4719","authenticated-orcid":false,"given":"Xiaoxia","family":"Sun","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-7327","authenticated-orcid":false,"given":"Maneesh","family":"Agrawala","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA and Stanford University, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1221-7256","authenticated-orcid":false,"given":"Kiran","family":"Bhat","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0952-2181","authenticated-orcid":false,"given":"Tinghui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Roblox, San Mateo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_1_2_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arxiv:https:\/\/arXiv.org\/abs\/2308.12966\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_3_1_3_1","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. arxiv:https:\/\/arXiv.org\/abs\/2511.16719\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2511.16719"},{"key":"e_1_3_3_1_4_1","unstructured":"Angel\u00a0X. Chang Thomas Funkhouser Leonidas Guibas Pat Hanrahan Qixing Huang Zimo Li Silvio Savarese Manolis Savva Shuran Song Hao Su Jianxiong Xiao Li Yi and Fisher Yu. 2015. ShapeNet: An Information-Rich 3D Model Repository. arxiv:https:\/\/arXiv.org\/abs\/1512.03012\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/1512.03012"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00552"},{"key":"e_1_3_3_1_6_1","volume-title":"Proceedings of the 39th International Conference on Neural Information Processing Systems","author":"Chen Minghao","year":"2025","unstructured":"Minghao Chen, Jianyuan Wang, Roman Shapovalov, Tom Monnier, Hyunyoung Jung, Dilin Wang, Rakesh Ranjan, Iro Laina, and Andrea Vedaldi. 2025b. AutoPartGen: Autogressive 3D Part Generation and Discovery. In Proceedings of the 39th International Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"crossref","unstructured":"Yongwei Chen Tengfei Wang Tong Wu Xingang Pan Kui Jia and Ziwei Liu. 2024. ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2403.12409\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2403.12409","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"crossref","unstructured":"Jasmine Collins Shubham Goel Kenan Deng Achleshwar Luthra Leon Xu Erhan Gundogdu Xi Zhang Tomas F.\u00a0Yago Vicente Thomas Dideriksen Himanshu Arora Matthieu Guillaumin and Jitendra Malik. 2022. ABO: Dataset and Benchmarks for Real-World 3D Object Understanding. arxiv:https:\/\/arXiv.org\/abs\/2110.06199\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2110.06199","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"e_1_3_3_1_9_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 Eli VanderBilt Aniruddha Kembhavi Carl Vondrick Georgia Gkioxari Kiana Ehsani Ludwig Schmidt and Ali Farhadi. 2023a. Objaverse-XL: A Universe of 10M+ 3D Objects. arxiv:https:\/\/arXiv.org\/abs\/2307.05663\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2307.05663","DOI":"10.52202\/075280-1554"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_1_11_1","unstructured":"Lihe Ding Shaocong Dong Yaokun Li Chenjian Gao Xiao Chen Rui Han Yihao Kuang Hong Zhang Bo Huang Zhanpeng Huang Zibin Wang Dan Xu and Tianfan Xue. 2025. FullPart: Generating each 3D Part at Full Resolution. arxiv:https:\/\/arXiv.org\/abs\/2510.26140\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2510.26140"},{"key":"e_1_3_3_1_12_1","doi-asserted-by":"crossref","unstructured":"Shaocong Dong Lihe Ding Xiao Chen Yaokun Li Yuxin Wang Yucheng Wang Qi Wang Jaehyeok Kim Chenjian Gao Zhanpeng Huang Zibin Wang Tianfan Xue and Dan Xu. 2025. From One to More: Contextual Part Latents for 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2507.08772\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2507.08772","DOI":"10.1109\/ICCV51701.2025.00771"},{"key":"e_1_3_3_1_13_1","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st 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, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 503, 28\u00a0pages."},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"crossref","unstructured":"Jun Gao Tianchang Shen Zian Wang Wenzheng Chen Kangxue Yin Daiqing Li Or Litany Zan Gojcic and Sanja Fidler. 2022. GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images. arxiv:https:\/\/arXiv.org\/abs\/2209.11163\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2209.11163","DOI":"10.52202\/068431-2308"},{"key":"e_1_3_3_1_15_1","unstructured":"Souhail Hadgi Bingchen Gong Ramana Sundararaman Emery Pierson Lei Li Peter Wonka and Maks Ovsjanikov. 2026. PatchAlign3D: Local Feature Alignment for Dense 3D Shape understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.02457 (2026)."},{"key":"e_1_3_3_1_16_1","unstructured":"Xufan He Yushuang Wu Xiaoyang Guo Chongjie Ye Jiaqing Zhou Tianlei Hu Xiaoguang Han and Dong Du. 2025a. UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents. arxiv:https:\/\/arXiv.org\/abs\/2512.09435\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2512.09435"},{"key":"e_1_3_3_1_17_1","unstructured":"Xianglong He Zi-Xin Zou Chia-Hao Chen Yuan-Chen Guo Ding Liang Chun Yuan Wanli Ouyang Yan-Pei Cao and Yangguang Li. 2025b. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling. arxiv:https:\/\/arXiv.org\/abs\/2503.21732\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2503.21732"},{"key":"e_1_3_3_1_18_1","unstructured":"Amir Hertz Or Perel Raja Giryes Olga Sorkine-Hornung and Daniel Cohen-Or. 2022. SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation. arxiv:https:\/\/arXiv.org\/abs\/2201.13168\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2201.13168"},{"key":"e_1_3_3_1_19_1","unstructured":"Ka-Hei Hui Ruihui Li Jingyu Hu and Chi-Wing Fu. 2022. Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes. arxiv:https:\/\/arXiv.org\/abs\/2206.04942\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2206.04942"},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_21_1","unstructured":"Juil Koo Seungwoo Yoo Minh\u00a0Hieu Nguyen and Minhyuk Sung. 2024. SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation. arxiv:https:\/\/arXiv.org\/abs\/2303.12236\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2303.12236"},{"key":"e_1_3_3_1_22_1","unstructured":"Zeqiang Lai Yunfei Zhao Zibo Zhao Haolin Liu Qingxiang Lin Jingwei Huang Chunchao Guo and Xiangyu Yue. 2025. LATTICE: Democratize High-Fidelity 3D Generation at Scale. arxiv:https:\/\/arXiv.org\/abs\/2512.03052\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2512.03052"},{"key":"e_1_3_3_1_23_1","first-page":"16816","volume-title":"International Conference on Learning Representations","volume":"2024","author":"Li Mingxiao","year":"2024","unstructured":"Mingxiao Li, Tingyu Qu, Ruicong Yao, Wei Sun, and Marie-Francine Moens. 2024. Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps. In International Conference on Learning Representations , B.\u00a0Kim, Y.\u00a0Yue, S.\u00a0Chaudhuri, K.\u00a0Fragkiadaki, M.\u00a0Khan, and Y.\u00a0Sun (Eds.), Vol.\u00a02024. 16816\u201316838. https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2024\/file\/483f8d2018d7025c87dd07e9b02fe4bf-Paper-Conference.pdf"},{"key":"e_1_3_3_1_24_1","unstructured":"Weiyu Li Jiarui Liu Hongyu Yan Rui Chen Yixun Liang Xuelin Chen Ping Tan and Xiaoxiao Long. 2025a. CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner. arxiv:https:\/\/arXiv.org\/abs\/2405.14979\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2405.14979"},{"key":"e_1_3_3_1_25_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:https:\/\/arXiv.org\/abs\/2505.07747\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.07747"},{"key":"e_1_3_3_1_26_1","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. 2025d. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models. arxiv:https:\/\/arXiv.org\/abs\/2502.06608\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2502.06608"},{"key":"e_1_3_3_1_27_1","unstructured":"Zhihao Li Yufei Wang Heliang Zheng Yihao Luo and Bihan Wen. 2025b. Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling. arxiv:https:\/\/arXiv.org\/abs\/2505.14521\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.14521"},{"key":"e_1_3_3_1_28_1","unstructured":"Chen-Hsuan Lin Jun Gao Luming Tang Towaki Takikawa Xiaohui Zeng Xun Huang Karsten Kreis Sanja Fidler Ming-Yu Liu and Tsung-Yi Lin. 2023. Magic3D: High-Resolution Text-to-3D Content Creation. arxiv:https:\/\/arXiv.org\/abs\/2211.10440\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.10440"},{"key":"e_1_3_3_1_29_1","volume-title":"Proceedings of the 39th International Conference on Neural Information Processing Systems","author":"Lin Yuchen","year":"2025","unstructured":"Yuchen Lin, Chenguo Lin, Panwang Pan, Honglei Yan, Yiqiang Feng, Yadong Mu, and Katerina Fragkiadaki. 2025. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers. In Proceedings of the 39th International Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657482"},{"key":"e_1_3_3_1_31_1","unstructured":"Ruoshi Liu Rundi Wu Basile\u00a0Van Hoorick Pavel Tokmakov Sergey Zakharov and Carl Vondrick. 2023b. Zero-1-to-3: Zero-shot One Image to 3D Object. arxiv:https:\/\/arXiv.org\/abs\/2303.11328\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2303.11328"},{"key":"e_1_3_3_1_32_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu Xingchao","year":"2023","unstructured":"Xingchao Liu, Chengyue Gong, and qiang liu. 2023a. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=XVjTT1nw5z"},{"key":"e_1_3_3_1_33_1","unstructured":"Changfeng Ma Yang Li Xinhao Yan Jiachen Xu Yunhan Yang Chunshi Wang Zibo Zhao Yanwen Guo Zhuo Chen and Chunchao Guo. 2025. P3-SAM: Native 3D Part Segmentation. arxiv:https:\/\/arXiv.org\/abs\/2509.06784\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2509.06784"},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"e_1_3_3_1_35_1","unstructured":"Kaichun Mo Shilin Zhu Angel\u00a0X. Chang Li Yi Subarna Tripathi Leonidas\u00a0J. Guibas and Hao Su. 2018. PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. arxiv:https:\/\/arXiv.org\/abs\/1812.02713\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1812.02713"},{"key":"e_1_3_3_1_36_1","doi-asserted-by":"crossref","unstructured":"Kiyohiro Nakayama Mikaela\u00a0Angelina Uy Jiahui Huang Shi-Min Hu Ke Li and Leonidas\u00a0J Guibas. 2023. DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2305.01921\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2305.01921","DOI":"10.1109\/ICCV51070.2023.01311"},{"key":"e_1_3_3_1_37_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 Herve Jegou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt Featured Certification."},{"key":"e_1_3_3_1_38_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T. Barron and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2209.14988\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2209.14988"},{"key":"e_1_3_3_1_39_1","unstructured":"Xuanchi Ren Jiahui Huang Xiaohui Zeng Ken Museth Sanja Fidler and Francis Williams. 2024. XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies. arxiv:https:\/\/arXiv.org\/abs\/2312.03806\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2312.03806"},{"key":"e_1_3_3_1_40_1","volume-title":"Proceedings of the 39th International Conference on Neural Information Processing Systems","author":"Tang Jiaxiang","year":"2025","unstructured":"Jiaxiang Tang, Ruijie Lu, Zhaoshuo Li, Zekun Hao, Xuan Li, Fangyin Wei, Shuran Song, Gang Zeng, Ming-Yu Liu, and Tsung-Yi Lin. 2025. Efficient Part-level 3D Object Generation via Dual Volume Packing. In Proceedings of the 39th International Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_1_41_1","unstructured":"Foundation\u00a0AI Team Kiran Bhat Nishchaie Khanna Karun Channa Tinghui Zhou Yiheng Zhu Xiaoxia Sun Charles Shang Anirudh Sudarshan Maurice Chu Daiqing Li Kangle Deng Jean-Philippe Fauconnier Tijmen Verhulsdonck Maneesh Agrawala Kayvon Fatahalian Alexander Weiss Christian Reiser Ravi\u00a0Kiran Chirravuri Ravali Kandur Alejandro Pelaez Akash Garg Michael Palleschi Jessica Wang Skylar Litz Leon Liu Anying Li David Harmon Derek Liu Liangjun Feng Denis Goupil Lukas Kuczynski Jihyun Yoon Naveen Marri Peiye Zhuang Yinan Zhang Brian Yin Haomiao Jiang Marcel van Workum Thomas Lane Bryce Erickson Salil Pathare Kyle Price Steve Han Yiqing Wang Anupam Singh and David Baszucki. 2025. Cube: A Roblox View of 3D Intelligence. arxiv:https:\/\/arXiv.org\/abs\/2503.15475\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2503.15475"},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"crossref","unstructured":"Zhengyi Wang Cheng Lu Yikai Wang Fan Bao Chongxuan Li Hang Su and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arxiv:https:\/\/arXiv.org\/abs\/2305.16213\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.16213","DOI":"10.52202\/075280-0368"},{"key":"e_1_3_3_1_43_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Sheng ming 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. arxiv:https:\/\/arXiv.org\/abs\/2508.02324\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.02324"},{"key":"e_1_3_3_1_44_1","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. arxiv:https:\/\/arXiv.org\/abs\/2505.17412\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.17412"},{"key":"e_1_3_3_1_45_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. 2025a. Native and Compact Structured Latents for 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2512.14692\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2512.14692"},{"key":"e_1_3_3_1_46_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. 2025b. Structured 3D Latents for Scalable and Versatile 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2412.01506\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.01506","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_1_47_1","unstructured":"Xinhao Yan Jiachen Xu Yang Li Changfeng Ma Yunhan Yang Chunshi Wang Zibo Zhao Zeqiang Lai Yunfei Zhao Zhuo Chen and Chunchao Guo. 2025. X-Part: high fidelity and structure coherent shape decomposition. arxiv:https:\/\/arXiv.org\/abs\/2509.08643\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2509.08643"},{"key":"e_1_3_3_1_48_1","unstructured":"Jianwei Yang Hao Zhang Feng Li Xueyan Zou Chunyuan Li and Jianfeng Gao. 2023. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V. arxiv:https:\/\/arXiv.org\/abs\/2310.11441\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2310.11441"},{"key":"e_1_3_3_1_49_1","unstructured":"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. 2025b. Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material. arxiv:https:\/\/arXiv.org\/abs\/2506.15442\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2506.15442"},{"key":"e_1_3_3_1_50_1","unstructured":"Yunhan Yang Yuan-Chen Guo Yukun Huang Zi-Xin Zou Zhipeng Yu Yangguang Li Yan-Pei Cao and Xihui Liu. 2025a. HoloPart: Generative 3D Part Amodal Segmentation. arxiv:https:\/\/arXiv.org\/abs\/2504.07943\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2504.07943"},{"key":"e_1_3_3_1_51_1","unstructured":"Yunhan Yang Yukun Huang Yuan-Chen Guo Liangjun Lu Xiaoyang Wu Edmund\u00a0Y. Lam Yan-Pei Cao and Xihui Liu. 2024. SAMPart3D: Segment Any Part in 3D Objects. arxiv:https:\/\/arXiv.org\/abs\/2411.07184\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2411.07184"},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763872"},{"key":"e_1_3_3_1_53_1","doi-asserted-by":"crossref","unstructured":"Li Yi Vladimir\u00a0G. Kim Duygu Ceylan I-Chao Shen Mengyan Yan Hao Su Cewu Lu Qixing Huang Alla Sheffer and Leonidas Guibas. 2016. A Scalable Active Framework for Region Annotation in 3D Shape Collections. SIGGRAPH Asia (2016).","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_3_3_1_54_1","doi-asserted-by":"crossref","unstructured":"Biao Zhang Jiapeng Tang Matthias Niessner and Peter Wonka. 2023. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2301.11445\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2301.11445","DOI":"10.1145\/3592442"},{"key":"e_1_3_3_1_55_1","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. arxiv:https:\/\/arXiv.org\/abs\/2406.13897\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2406.13897"},{"key":"e_1_3_3_1_56_1","doi-asserted-by":"publisher","unstructured":"Longwen Zhang Qixuan Zhang Haoran Jiang Yinuo Bai Wei Yang Lan Xu and Jingyi Yu. 2025a. BANG: Dividing 3D Assets via Generative Exploded Dynamics. ACM Transactions on Graphics 44 4 (July 2025) 1\u201321. 10.1145\/3730840","DOI":"10.1145\/3730840"},{"key":"e_1_3_3_1_57_1","unstructured":"Yibo Zhang Li Zhang Rui Ma and Nan Cao. 2025b. TexVerse: A Universe of 3D Objects with High-Resolution Textures. arxiv:https:\/\/arXiv.org\/abs\/2508.10868\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.10868"},{"key":"e_1_3_3_1_58_1","doi-asserted-by":"crossref","unstructured":"Zibo Zhao Wen Liu Xin Chen Xianfang Zeng Rui Wang Pei Cheng Bin Fu Tao Chen Gang Yu and Shenghua Gao. 2023. Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation. arxiv:https:\/\/arXiv.org\/abs\/2306.17115\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2306.17115","DOI":"10.52202\/075280-3236"}],"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":"2026-07-16T18:25:43Z","timestamp":1784226343000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":57,"alternative-id":["10.1145\/3799902.3811117","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811117","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"}}]}}