{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:13:43Z","timestamp":1783106023337,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":148,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61632003, 61375022, 61403005"],"award-info":[{"award-number":["61632003, 61375022, 61403005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763893","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Generating Objects with Part-Articulation from a Single Image"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2786-2937","authenticated-orcid":false,"given":"Ruijie","family":"Lu","sequence":"first","affiliation":[{"name":"State Key Lab of General AI, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2367-211X","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2487-4469","authenticated-orcid":false,"given":"Jiaxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0581-0974","authenticated-orcid":false,"given":"Junfeng","family":"Ni","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6097-4881","authenticated-orcid":false,"given":"Yuxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3640-0511","authenticated-orcid":false,"given":"Diwen","family":"Wan","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9575-4651","authenticated-orcid":false,"given":"Gang","family":"Zeng","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8176-0241","authenticated-orcid":false,"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Beijing Institute for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-7148","authenticated-orcid":false,"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Lab of General AI, Beijing Institute for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_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_3_1","unstructured":"Niket Agarwal Arslan Ali Maciej Bala Yogesh Balaji Erik Barker Tiffany Cai Prithvijit Chattopadhyay Yongxin Chen Yin Cui Yifan Ding et\u00a0al. 2025. Cosmos world foundation model platform for physical ai. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03575 (2025)."},{"key":"e_1_3_3_2_4_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Bahmani Sherwin","year":"2024","unstructured":"Sherwin Bahmani, Xian Liu, Wang Yifan, Ivan Skorokhodov, Victor Rong, Ziwei Liu, Xihui Liu, Jeong\u00a0Joon Park, Sergey Tulyakov, Gordon Wetzstein, et\u00a0al. 2024a. Tc4d: Trajectory-conditioned text-to-4d generation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"e_1_3_3_2_6_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Joseph Dabis Chelsea Finn Keerthana Gopalakrishnan Karol Hausman Alex Herzog Jasmine Hsu et\u00a0al. 2022. Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.06817 (2022).","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01515"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00142"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.124"},{"key":"e_1_3_3_2_13_1","volume-title":"Blender - a 3D modelling and rendering package","author":"Community Blender\u00a0Online","year":"2018","unstructured":"Blender\u00a0Online Community. 2018. Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam. http:\/\/www.blender.org"},{"key":"e_1_3_3_2_14_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Deitke Matt","year":"2023","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir\u00a0Yitzhak Gadre, et\u00a0al. 2023a. Objaverse-xl: A universe of 10m+ 3d objects. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_16_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Deng Jianning","year":"2024","unstructured":"Jianning Deng, Kartic Subr, and Hakan Bilen. 2024. Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Jiafei Duan Samson Yu Hui\u00a0Li Tan Hongyuan Zhu and Cheston Tan. 2022. A survey of embodied ai: From simulators to research tasks. IEEE Transactions on Emerging Topics in Computational Intelligence 6 2 (2022) 230\u2013244.","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"e_1_3_3_2_18_1","volume-title":"Robotics: Science and Systems (RSS)","author":"Eisner Ben","year":"2022","unstructured":"Ben Eisner, Harry Zhang, and David Held. 2022. Flowbot3d: Learning 3d articulation flow to manipulate articulated objects. In Robotics: Science and Systems (RSS)."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_3_2_20_1","unstructured":"Yifei Feng Mingxin Yang Shuhui Yang Sheng Zhang Jiaao Yu Zibo Zhao Yuhong Liu Jie Jiang and Chunchao Guo. 2025. RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.19011 (2025)."},{"key":"e_1_3_3_2_21_1","unstructured":"Daoyi Gao Yawar Siddiqui Lei Li and Angela Dai. 2024. MeshArt: Generating Articulated Meshes with Structure-guided Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.11596 (2024)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00657"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00684"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02528"},{"key":"e_1_3_3_2_26_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Zhengyang Liang Yaohui Wang Yu Qiao Maneesh Agrawala Dahua Lin and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.04725 (2023)."},{"key":"e_1_3_3_2_27_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. 2025. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.21732 (2025)."},{"key":"e_1_3_3_2_28_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_29_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hong Wenyi","year":"2023","unstructured":"Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, and Jie Tang. 2023a. Cogvideo: Large-scale pretraining for text-to-video generation via transformers. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_30_1","unstructured":"Yicong Hong Kai Zhang Jiuxiang Gu Sai Bi Yang Zhou Difan Liu Feng Liu Kalyan Sunkavalli Trung Bui and Hao Tan. 2023b. 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_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02288"},{"key":"e_1_3_3_2_33_1","unstructured":"Jiangyong Huang Xiaojian Ma Xiongkun Linghu Yue Fan Junchao He Wenxin Tan Qing Li Song-Chun Zhu Yixin Chen Baoxiong Jia et\u00a0al. 2025b. LEO-VL: Towards 3D Vision-Language Generalists via Data Scaling with Efficient Representation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09935 (2025)."},{"key":"e_1_3_3_2_34_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang Jiangyong","year":"2023","unstructured":"Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang. 2023. An embodied generalist agent in 3d world. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_40_1","unstructured":"Diederik\u00a0P Kingma Max Welling et\u00a0al. 2013. Auto-encoding variational bayes."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_42_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_43_1","doi-asserted-by":"crossref","unstructured":"Samuli Laine Janne Hellsten Tero Karras Yeongho Seol Jaakko Lehtinen and Timo Aila. 2020. Modular primitives for high-performance differentiable rendering. ACM Transactions on Graphics (ToG) 39 6 (2020) 1\u201314.","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_3_2_44_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Le Long","year":"2025","unstructured":"Long Le, Jason Xie, William Liang, Hung-Ju Wang, Yue Yang, Yecheng\u00a0Jason Ma, Kyle Vedder, Arjun Krishna, Dinesh Jayaraman, and Eric Eaton. 2025. Articulate-anything: Automatic modeling of articulated objects via a vision-language foundation model. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_45_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Li Bing","year":"2024","unstructured":"Bing Li, Cheng Zheng, Wenxuan Zhu, Jinjie Mai, Biao Zhang, Peter Wonka, and Bernard Ghanem. 2024f. Vivid-zoo: Multi-view video generation with diffusion model. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801835"},{"key":"e_1_3_3_2_47_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Li Ruining","year":"2024","unstructured":"Ruining Li, Chuanxia Zheng, Christian Rupprecht, and Andrea Vedaldi. 2024d. Dragapart: Learning a part-level motion prior for articulated objects. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_48_1","unstructured":"Ruining Li Chuanxia Zheng Christian Rupprecht and Andrea Vedaldi. 2024e. Puppet-master: Scaling interactive video generation as a motion prior for part-level dynamics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.04631 (2024)."},{"key":"e_1_3_3_2_49_1","unstructured":"Yishu Li Wen\u00a0Hui Leng Yiming Fang Ben Eisner and David Held. 2024b. FlowBotHD: History-Aware Diffuser Handling Ambiguities in Articulated Objects Manipulation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.07078 (2024)."},{"key":"e_1_3_3_2_50_1","unstructured":"Yangguang Li Zi-Xin Zou Zexiang Liu Dehu Wang Yuan Liang Zhipeng Yu Xingchao Liu Yuan-Chen Guo Ding Liang Wanli Ouyang et\u00a0al. 2025. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06608 (2025)."},{"key":"e_1_3_3_2_51_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Li Zhiqi","year":"2024","unstructured":"Zhiqi Li, Yiming Chen, and Peidong Liu. 2024a. Dreammesh4d: Video-to-4d generation with sparse-controlled gaussian-mesh hybrid representation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_52_1","unstructured":"Xinyu Lian Zichao Yu Ruiming Liang Yitong Wang Li\u00a0Ray Luo Kaixu Chen Yuanzhen Zhou Qihong Tang Xudong Xu Zhaoyang Lyu et\u00a0al. 2025. Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.13424 (2025)."},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"e_1_3_3_2_54_1","unstructured":"Shengjie Lin Jiading Fang Muhammad\u00a0Zubair Irshad Vitor\u00a0Campagnolo Guizilini Rares\u00a0Andrei Ambrus Greg Shakhnarovich and Matthew\u00a0R Walter. 2025a. SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.03594 (2025)."},{"key":"e_1_3_3_2_55_1","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.05573 (2025)."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"e_1_3_3_2_57_1","unstructured":"Yaron Lipman Ricky\u00a0TQ Chen Heli Ben-Hamu Maximilian Nickel and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02747 (2022)."},{"key":"e_1_3_3_2_58_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu Jiayi","year":"2025","unstructured":"Jiayi Liu, Denys Iliash, Angel\u00a0X Chang, Manolis Savva, and Ali Mahdavi-Amiri. 2025a. SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00039"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01693"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"e_1_3_3_2_62_1","unstructured":"Minghua Liu Mikaela\u00a0Angelina Uy Donglai Xiang Hao Su Sanja Fidler Nicholas Sharp and Jun Gao. 2025c. PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.11451 (2025)."},{"key":"e_1_3_3_2_63_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Liu Minghua","year":"2023","unstructured":"Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Mukund Varma\u00a0T, Zexiang Xu, and Hao Su. 2023d. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_65_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_66_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Liu Yu","year":"2024","unstructured":"Yu Liu, Baoxiong Jia, Yixin Chen, and Siyuan Huang. 2024a. SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_67_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu Yu","year":"2025","unstructured":"Yu Liu, Baoxiong Jia, Ruijie Lu, Junfeng Ni, Song-Chun Zhu, and Siyuan Huang. 2025b. Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_68_1","unstructured":"Yuan Liu Cheng Lin Zijiao Zeng Xiaoxiao Long Lingjie Liu Taku Komura and Wenping Wang. 2023a. Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.03453 (2023)."},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_70_1","unstructured":"Ruijie Lu Yixin Chen Yu Liu Jiaxiang Tang Junfeng Ni Diwen Wan Gang Zeng and Siyuan Huang. 2025. Taco: Taming diffusion for in-the-wild video amodal completion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.12049 (2025)."},{"key":"e_1_3_3_2_71_1","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lu Ruijie","year":"2024","unstructured":"Ruijie Lu, Yixin Chen, Junfeng Ni, Baoxiong Jia, Yu Liu, Diwen Wan, Gang Zeng, and Siyuan Huang. 2024. Movis: Enhancing multi-object novel view synthesis for indoor scenes. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_3_2_73_1","unstructured":"Rundong Luo Haoran Geng Congyue Deng Puhao Li Zan Wang Baoxiong Jia Leonidas Guibas and Siyuan Huang. 2024. Physpart: Physically plausible part completion for interactable objects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.13724 (2024)."},{"key":"e_1_3_3_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00194"},{"key":"e_1_3_3_2_75_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Mandi Zhao","year":"2025","unstructured":"Zhao Mandi, Yijia Weng, Dominik Bauer, and Shuran Song. 2025. Real2code: Reconstruct articulated objects via code generation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_77_1","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Mo Kaichun","year":"2020","unstructured":"Kaichun Mo, Shilin Zhu, Angel\u00a0X Chang, Li Yi, Subarna Tripathi, Leonidas\u00a0J Guibas, and Hao Su. 2020. Partnet: A large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_78_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Mou Chong","year":"2024","unstructured":"Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, and Jian Zhang. 2024. Dragondiffusion: Enabling drag-style manipulation on diffusion models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_79_1","unstructured":"Junfeng Ni Yixin Chen Bohan Jing Nan Jiang Bin Wang Bo Dai Puhao Li Yixin Zhu Song-Chun Zhu and Siyuan Huang. 2024. Phyrecon: Physically plausible neural scene reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.16666 (2024)."},{"key":"e_1_3_3_2_80_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"e_1_3_3_2_82_1","unstructured":"Weikun Peng Jun Lv Cewu Lu and Manolis Savva. 2025. Generalizable Articulated Object Reconstruction from Casually Captured RGBD Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.08334 (2025)."},{"key":"e_1_3_3_2_83_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_84_1","volume-title":"International Conference on Learning Representations (ICLR)","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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_85_1","unstructured":"Guocheng Qian Jinjie Mai Abdullah Hamdi Jian Ren Aliaksandr Siarohin Bing Li Hsin-Ying Lee Ivan Skorokhodov Peter Wonka Sergey Tulyakov et\u00a0al. 2023. Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.17843 (2023)."},{"key":"e_1_3_3_2_86_1","unstructured":"Xiaowen Qiu Jincheng Yang Yian Wang Zhehuan Chen Yufei Wang Tsun-Hsuan Wang Zhou Xian and Chuang Gan. 2025. Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.02590 (2025)."},{"key":"e_1_3_3_2_87_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_88_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ravi Nikhila","year":"2025","unstructured":"Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman R\u00e4dle, Chloe Rolland, Laura Gustafson, et\u00a0al. 2025. Sam 2: Segment anything in images and videos. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_89_1","unstructured":"Jiawei Ren Liang Pan Jiaxiang Tang Chi Zhang Ang Cao Gang Zeng and Ziwei Liu. 2023. Dreamgaussian4d: Generative 4d gaussian splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17142 (2023)."},{"key":"e_1_3_3_2_90_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ren Jiawei","year":"2024","unstructured":"Jiawei Ren, Cheng Xie, Ashkan Mirzaei, Karsten Kreis, Ziwei Liu, Antonio Torralba, Sanja Fidler, Seung\u00a0Wook Kim, Huan Ling, et\u00a0al. 2024. L4gm: Large 4d gaussian reconstruction model. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_92_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_2_93_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et\u00a0al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_94_1","unstructured":"Team Seawead Ceyuan Yang Zhijie Lin Yang Zhao Shanchuan Lin Zhibei Ma Haoyuan Guo Hao Chen Lu Qi Sen Wang et\u00a0al. 2025. Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.08685 (2025)."},{"key":"e_1_3_3_2_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02127"},{"key":"e_1_3_3_2_96_1","volume-title":"International Conference on Computer Vision (ICCV)","author":"Shen Hongyu","year":"2025","unstructured":"Hongyu Shen, Junfeng Ni, Yixin Chen, Weishuo Li, Mingtao Pei, and Siyuan Huang. 2025. Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing. In International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_3_2_97_1","unstructured":"Ruoxi Shi Hansheng Chen Zhuoyang Zhang Minghua Liu Chao Xu Xinyue Wei Linghao Chen Chong Zeng and Hao Su. 2023a. Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.15110 (2023)."},{"key":"e_1_3_3_2_98_1","unstructured":"Yichun Shi Peng Wang Jianglong Ye Mai Long Kejie Li and Xiao Yang. 2023b. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.16512 (2023)."},{"key":"e_1_3_3_2_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"e_1_3_3_2_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00515"},{"key":"e_1_3_3_2_101_1","unstructured":"George Tang William Zhao Logan Ford David Benhaim and Paul Zhang. 2024d. Segment any mesh: Zero-shot mesh part segmentation via lifting segment anything 2 to 3d. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.13679 (2024)."},{"key":"e_1_3_3_2_102_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, and Ziwei Liu. 2024a. Lgm: Large multi-view gaussian model for high-resolution 3d content creation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_103_1","unstructured":"Jiaxiang Tang Ruijie Lu Xiaokang Chen Xiang Wen Gang Zeng and Ziwei Liu. 2024b. Intex: Interactive text-to-texture synthesis via unified depth-aware inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.11878 (2024)."},{"key":"e_1_3_3_2_104_1","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09980 (2025)."},{"key":"e_1_3_3_2_105_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2024c. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00227"},{"key":"e_1_3_3_2_107_1","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.01717 (2018)."},{"key":"e_1_3_3_2_108_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Van\u00a0Hoorick Basile","year":"2024","unstructured":"Basile Van\u00a0Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel Tokmakov, Achal Dave, Changxi Zheng, and Carl Vondrick. 2024. Generative camera dolly: Extreme monocular dynamic novel view synthesis. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_109_1","doi-asserted-by":"crossref","unstructured":"Kai von Szadkowski and Simon Reichel. 2020. Phobos: A tool for creating complex robot models. Journal of Open Source Software 5 45 (2020) 1326.","DOI":"10.21105\/joss.01326"},{"key":"e_1_3_3_2_110_1","unstructured":"Aditya Vora Sauradip Nag and Hao Zhang. 2025. Articulate That Object Part (ATOP): 3D Part Articulation from Text and Motion Personalization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.07278 (2025)."},{"key":"e_1_3_3_2_111_1","unstructured":"Diwen Wan Ruijie Lu and Gang Zeng. 2024a. Superpoint gaussian splatting for real-time high-fidelity dynamic scene reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.03697 (2024)."},{"key":"e_1_3_3_2_112_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wan Diwen","year":"2024","unstructured":"Diwen Wan, Yuxiang Wang, Ruijie Lu, and Gang Zeng. 2024b. Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_113_1","unstructured":"Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng et\u00a0al. 2025a. 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_114_1","unstructured":"Haowen Wang Xiaoping Yuan Zhao Jin Zhen Zhao Zhengping Che Yousong Xue Jin Tian Yakun Huang and Jian Tang. 2025b. Self-Supervised Multi-Part Articulated Objects Modeling via Deformable Gaussian Splatting and Progressive Primitive Segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09663 (2025)."},{"key":"e_1_3_3_2_115_1","unstructured":"Jiuniu Wang Hangjie Yuan Dayou Chen Yingya Zhang Xiang Wang and Shiwei Zhang. 2023b. Modelscope text-to-video technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06571 (2023)."},{"key":"e_1_3_3_2_116_1","unstructured":"Peng Wang and Yichun Shi. 2023. Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02201 (2023)."},{"key":"e_1_3_3_2_117_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Wang Qi","year":"2024","unstructured":"Qi Wang, Ruijie Lu, Xudong Xu, Jingbo Wang, Michael\u00a0Yu Wang, Bo Dai, Gang Zeng, and Dan Xu. 2024. Roomtex: Texturing compositional indoor scenes via iterative inpainting. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_118_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. Transactions on Image Processing (TIP) 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_119_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang Zhengyi","year":"2023","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. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_120_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00303"},{"key":"e_1_3_3_2_121_1","unstructured":"Di Wu Liu Liu Zhou Linli Anran Huang Liangtu Song Qiaojun Yu Qi Wu and Cewu Lu. 2025. REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.06677 (2025)."},{"key":"e_1_3_3_2_122_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wu Kailu","year":"2024","unstructured":"Kailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang, Yating Hu, Yueqi Duan, and Kaisheng Ma. 2024a. Unique3d: High-quality and efficient 3d mesh generation from a single image. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_123_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Wu Zijie","year":"2024","unstructured":"Zijie Wu, Chaohui Yu, Yanqin Jiang, Chenjie Cao, Fan Wang, and Xiang Bai. 2024b. Sc4d: Sparse-controlled video-to-4d generation and motion transfer. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_124_1","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xia Hongchi","year":"2024","unstructured":"Hongchi Xia, Entong Su, Marius Memmel, Arhan Jain, Raymond Yu, Numfor Mbiziwo-Tiapo, Ali Farhadi, Abhishek Gupta, Shenlong Wang, and Wei-Chiu Ma. 2024. Drawer: Digital reconstruction and articulation with environment realism. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"e_1_3_3_2_126_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_127_1","doi-asserted-by":"crossref","unstructured":"Xuan Xiao Jiahang Liu Zhipeng Wang Yanmin Zhou Yong Qi Shuo Jiang Bin He and Qian Cheng. 2025. Robot learning in the era of foundation models: A survey. Neurocomputing (2025) 129963.","DOI":"10.1016\/j.neucom.2025.129963"},{"key":"e_1_3_3_2_128_1","unstructured":"Yiming Xie Chun-Han Yao Vikram Voleti Huaizu Jiang and Varun Jampani. 2024. Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.17470 (2024)."},{"key":"e_1_3_3_2_129_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Xing Jinbo","year":"2024","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2024. Dynamicrafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_130_1","volume-title":"European Conference on Computer Vision","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Zifan Shi, Wang Yifan, Hansheng Chen, Ceyuan Yang, Sida Peng, Yujun Shen, and Gordon Wetzstein. 2024. Grm: Large gaussian reconstruction model for efficient 3d reconstruction and generation. In European Conference on Computer Vision."},{"key":"e_1_3_3_2_131_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2504.07943 (2025)."},{"key":"e_1_3_3_2_132_1","unstructured":"Yunhan Yang Yukun Huang Yuan-Chen Guo Liangjun Lu Xiaoyang Wu Edmund\u00a0Y Lam Yan-Pei Cao and Xihui Liu. 2024a. Sampart3d: Segment any part in 3d objects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.07184 (2024)."},{"key":"e_1_3_3_2_133_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01539"},{"key":"e_1_3_3_2_134_1","doi-asserted-by":"crossref","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.06165 (2025).","DOI":"10.1145\/3757377.3763872"},{"key":"e_1_3_3_2_135_1","unstructured":"Chun-Han Yao Yiming Xie Vikram Voleti Huaizu Jiang and Varun Jampani. 2025. SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.16396 (2025)."},{"key":"e_1_3_3_2_136_1","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.22236 3 (2025)."},{"key":"e_1_3_3_2_137_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"e_1_3_3_2_138_1","volume-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yu Huangyue","year":"2024","unstructured":"Huangyue Yu, Baoxiong Jia, Yixin Chen, Yandan Yang, Puhao Li, Rongpeng Su, Jiaxin Li, Qing Li, Wei Liang, Song-Chun Zhu, et\u00a0al. 2024. METASCENES: Towards Automated Replica Creation for Real-world 3D Scans. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_139_1","unstructured":"Tianjiao Yu Vedant Shah Muntasir Wahed Ying Shen Kiet\u00a0A Nguyen and Ismini Lourentzou. 2025. Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.17212 (2025)."},{"key":"e_1_3_3_2_140_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zeng Yifei","year":"2024","unstructured":"Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, and Yao Yao. 2024. Stag4d: Spatial-temporal anchored generative 4d gaussians. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_141_1","doi-asserted-by":"crossref","unstructured":"Biao Zhang Jiapeng Tang Matthias Niessner and Peter Wonka. 2023b. 3dshape2vecset: A 3d shape representation for neural fields and generative diffusion models. ACM Transactions On Graphics (TOG) 42 4 (2023) 1\u201316.","DOI":"10.1145\/3592442"},{"key":"e_1_3_3_2_142_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhang Haiyu","year":"2024","unstructured":"Haiyu Zhang, Xinyuan Chen, Yaohui Wang, Xihui Liu, Yunhong Wang, and Yu Qiao. 2024a. 4diffusion: Multi-view video diffusion model for 4d generation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_143_1","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2025. Packing Input Frame Context in Next-Frame Prediction Models for Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12626 (2025)."},{"key":"e_1_3_3_2_144_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_145_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. 2024b. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. ACM Transactions on Graphics (TOG) (2024).","DOI":"10.1145\/3658146"},{"key":"e_1_3_3_2_146_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_147_1","unstructured":"Shiwei Zhang Jiayu Wang Yingya Zhang Kang Zhao Hangjie Yuan Zhiwu Qin Xiang Wang Deli Zhao and Jingren Zhou. 2023c. I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.04145 (2023)."},{"key":"e_1_3_3_2_148_1","unstructured":"Yuyang Zhao Zhiwen Yan Enze Xie Lanqing Hong Zhenguo Li and Gim\u00a0Hee Lee. 2023. Animate124: Animating one image to 4d dynamic scene. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.14603 (2023)."},{"key":"e_1_3_3_2_149_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)."}],"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\/3757377.3763893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:25:36Z","timestamp":1765250736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":148,"alternative-id":["10.1145\/3757377.3763893","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763893","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"}}]}}