{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:04:55Z","timestamp":1784228695178,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation of China (NSFC)","award":["62125107"],"award-info":[{"award-number":["62125107"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811152","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":["Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8906-657X","authenticated-orcid":false,"given":"Siyou","family":"Lin","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3157-6606","authenticated-orcid":false,"given":"Zhou","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8633-4551","authenticated-orcid":false,"given":"Hongwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1028-3759","authenticated-orcid":false,"given":"Liang","family":"An","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9967-1145","authenticated-orcid":false,"given":"Dongping","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5350-6809","authenticated-orcid":false,"given":"Shaohui","family":"Jiao","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3215-0225","authenticated-orcid":false,"given":"Yebin","family":"Liu","sequence":"additional","affiliation":[{"name":"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","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.08113 (2023)."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_3_2_4_1","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.23306 (2025)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"e_1_3_3_2_6_1","volume-title":"The Fourteenth International Conference on Learning Representations","author":"Chen Xingyu","year":"2026","unstructured":"Xingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger, and Anpei Chen. 2026. TTT3R: 3D Reconstruction as Test-Time Training. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=aMs6FtNaY5"},{"key":"e_1_3_3_2_7_1","unstructured":"Yiwen Chen Zhihao Li Yikai Wang Hu Zhang Qin Li Chi Zhang and Guosheng Lin. 2025. Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention. arxiv:https:\/\/arXiv.org\/abs\/2507.17745\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2507.17745"},{"key":"e_1_3_3_2_8_1","unstructured":"Timoth\u00e9e Darcet Maxime Oquab Julien Mairal and Piotr Bojanowski. 2023. Vision Transformers Need Registers."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Laura Downs Anthony Francis Nate Koenig Brandon Kinman Ryan\u00a0Michael Hickman Krista Reymann Thomas\u00a0Barlow McHugh and Vincent Vanhoucke. 2022. Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items. 2022 International Conference on Robotics and Automation (ICRA) (2022) 2553\u20132560. https:\/\/api.semanticscholar.org\/CorpusID:248392390","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_26"},{"key":"e_1_3_3_2_13_1","volume-title":"The Twelfth International Conference on Learning Representations","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. https:\/\/openreview.net\/forum?id=sllU8vvsFF"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","unstructured":"Jingyu Hu Ka-Hei Hui Zhengzhe Liu Ruihui Li and Chi-Wing Fu. 2024. Neural Wavelet-domain Diffusion for 3D Shape Generation Inversion and Manipulation. ACM Trans. Graph. 43 2 Article 16 (Jan. 2024) 18\u00a0pages. 10.1145\/3635304","DOI":"10.1145\/3635304"},{"key":"e_1_3_3_2_15_1","unstructured":"Binbin Huang Haobin Duan Yiqun Zhao Zibo Zhao Yi Ma and Shenghua Gao. 2025. CUPID: Pose-Grounded Generative 3D Reconstruction from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.20776 (2025)."},{"key":"e_1_3_3_2_16_1","unstructured":"Jiaxin Huang Yuanbo Yang Bangbang Yang Lin Ma Yuewen Ma and Yiyi Liao. 2026. Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction. ArXiv abs\/2601.04090 (2026). https:\/\/api.semanticscholar.org\/CorpusID:284532394"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Hanwen Jiang Zhenyu Jiang Kristen Grauman and Yuke Zhu. 2024a. Few-View Object Reconstruction with Unknown Categories and Camera Poses. International Conference on 3D Vision (3DV) (2024).","DOI":"10.1109\/3DV62453.2024.00055"},{"key":"e_1_3_3_2_18_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang Hanwen","year":"2024","unstructured":"Hanwen Jiang, Zhenyu Jiang, Yue Zhao, and Qixing Huang. 2024b. LEAP: Liberate Sparse-View 3D Modeling from Camera Poses. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KPmajBxEaF"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Lihan Jiang Yucheng Mao Linning Xu Tao Lu Kerui Ren Yichen Jin Xudong Xu Mulin Yu Jiangmiao Pang Feng Zhao et\u00a0al. 2025. AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23716 (2025).","DOI":"10.1145\/3763326"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Cijo Jose Th\u00e9o Moutakanni Dahyun Kang Federico Baldassarre Timoth\u00e9e Darcet Hu Xu Daniel Li Marc Szafraniec Micha\u00ebl Ramamonjisoa Maxime Oquab Oriane Sim\u00e9oni Huy\u00a0V. Vo Patrick Labatut and Piotr Bojanowski. 2024. DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment.","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Nikhil Keetha Norman M\u00fcller Johannes Sch\u00f6nberger Lorenzo Porzi Yuchen Zhang Tobias Fischer Arno Knapitsch Duncan Zauss Ethan Weber Nelson Antunes Jonathon Luiten Manuel Lopez-Antequera Samuel\u00a0Rota Bul\u00f2 Christian Richardt Deva Ramanan Sebastian Scherer and Peter Kontschieder. 2025. MapAnything: Universal Feed-Forward Metric 3D Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.13414.","DOI":"10.1109\/3DV69130.2026.00054"},{"key":"e_1_3_3_2_22_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 Transactions on Graphics 42 4 (July 2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","unstructured":"Vincent Lepetit Francesc Moreno-Noguer and Pascal Fua. 2009. EPnP: An Accurate O(n) Solution to the PnP Problem. Int. J. Comput. Vision 81 2 (Feb. 2009) 155\u2013166. 10.1007\/s11263-008-0152-6","DOI":"10.1007\/s11263-008-0152-6"},{"key":"e_1_3_3_2_24_1","unstructured":"Baicheng Li Dong Wu Jun Li Shunkai Zhou Zecui Zeng Lusong Li and Hongbin Zha. 2026. MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2603.11633 (2026)."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"e_1_3_3_2_26_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2505.14521 (2025)."},{"key":"e_1_3_3_2_27_1","unstructured":"Weixin Liang Lili Yu Liang Luo Srini Iyer Ning Dong Chunting Zhou Gargi Ghosh Mike Lewis Wen tau Yih Luke Zettlemoyer and Xi\u00a0Victoria Lin. 2025. Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. Transactions on Machine Learning Research (2025). https:\/\/openreview.net\/forum?id=Nu6N69i8SB"},{"key":"e_1_3_3_2_28_1","unstructured":"Haotong Lin Sili Chen Jun\u00a0Hao Liew Donny\u00a0Y. Chen Zhenyu Li Guang Shi Jiashi Feng and Bingyi Kang. 2025. Depth Anything 3: recovering the visual space from any views. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.10647 (2025)."},{"key":"e_1_3_3_2_29_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman Yaron","year":"2023","unstructured":"Yaron Lipman, Ricky T.\u00a0Q. Chen, Heli Ben-Hamu, Maximilian Nickel, and Matthew Le. 2023. Flow Matching for Generative Modeling. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PqvMRDCJT9t"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"e_1_3_3_2_33_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Theo Moutakanni Huy\u00a0V. Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Russell Howes Po-Yao Huang Hu Xu Vasu Sharma Shang-Wen Li Wojciech Galuba Mike Rabbat Mido Assran Nicolas Ballas Gabriel Synnaeve Ishan Misra Herve Jegou Julien Mairal Patrick Labatut Armand Joulin and Piotr Bojanowski. 2023. DINOv2: Learning Robust Visual Features without Supervision."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Stanislav Pidhorskyi Tomas Simon Gabriel Schwartz He Wen Yaser Sheikh and Jason Saragih. 2024. Rasterized Edge Gradients: Handling Discontinuities Differentiably. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.02508 (2024).","DOI":"10.1007\/978-3-031-73010-8_20"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_3_2_38_1","unstructured":"SAM3DTeam 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. (2025). arxiv:https:\/\/arXiv.org\/abs\/2511.16624\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00839"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"e_1_3_3_2_43_1","volume-title":"International Conference on Learning Representations","author":"Skorokhodov Ivan","year":"2023","unstructured":"Ivan Skorokhodov, Aliaksandr Siarohin, Yinghao Xu, Jian Ren, Hsin-Ying Lee, Peter Wonka, and Sergey Tulyakov. 2023. 3D generation on ImageNet. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=U2WjB9xxZ9q"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Stefan Stojanov Anh Thai and James\u00a0M. Rehg. 2021. Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias. (2021).","DOI":"10.1109\/CVPR46437.2021.00184"},{"key":"e_1_3_3_2_45_1","unstructured":"Zhicong Tang Shuyang Gu Chunyu Wang Ting Zhang Jianmin Bao Dong Chen and Baining Guo. 2023. VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder. arxiv:https:\/\/arXiv.org\/abs\/2312.11459\u00a0[cs.CV]"},{"key":"e_1_3_3_2_46_1","unstructured":"Tencent\u00a0Hunyuan3D Team. 2024. Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2411.02293\u00a0[cs.CV]"},{"key":"e_1_3_3_2_47_1","unstructured":"Tencent\u00a0Hunyuan3D Team. 2025a. Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation. arxiv:https:\/\/arXiv.org\/abs\/2501.12202\u00a0[cs.CV]"},{"key":"e_1_3_3_2_48_1","unstructured":"Tencent\u00a0Hunyuan3D Team. 2025b. Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details. arxiv:https:\/\/arXiv.org\/abs\/2506.16504\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2506.16504"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"crossref","unstructured":"Jianyuan Wang Christian Rupprecht and David Novotny. 2023a. PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment. ICCV.","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"e_1_3_3_2_51_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Hao Tan, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, and Kai Zhang. 2024b. PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=noe76eRcPC"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"e_1_3_3_2_55_1","unstructured":"Weijie Wang Yeqing Chen Zeyu Zhang Hengyu Liu Haoxiao Wang Zhiyuan Feng Wenkang Qin Zheng Zhu Donny\u00a0Y. Chen and Bohan Zhuang. 2025b. VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.19297 (2025)."},{"key":"e_1_3_3_2_56_1","unstructured":"Yifan Wang Jianjun Zhou Haoyi Zhu Wenzheng Chang Yang Zhou Zizun Li Junyi Chen Jiangmiao Pang Chunhua Shen and Tong He. 2025d. \u03c03: Scalable Permutation-Equivariant Visual Geometry Learning. arxiv:https:\/\/arXiv.org\/abs\/2507.13347\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2507.13347"},{"key":"e_1_3_3_2_57_1","unstructured":"Guanjun Wu Jiemin Fang Chen Yang Sikuang Li Taoran Yi Jia Lu Zanwei Zhou Jiazhong Cen Lingxi Xie Xiaopeng Zhang Wei Wei Wenyu Liu Xinggang Wang and Qi Tian. 2025a. UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.25079 (2025)."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157106"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"e_1_3_3_2_60_1","unstructured":"Shuang Wu Youtian Lin Feihu Zhang Yifei Zeng Yikang Yang Yajie Bao Jiachen Qian Siyu Zhu Philip Torr Xun Cao and Yao Yao. 2025b. Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.17412 (2025)."},{"key":"e_1_3_3_2_61_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. Tech report (2025)."},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_9"},{"key":"e_1_3_3_2_66_1","unstructured":"Jiale Xu Weihao Cheng Yiming Gao Xintao Wang Shenghua Gao and Ying Shan. 2024a. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.07191 (2024)."},{"key":"e_1_3_3_2_67_1","unstructured":"Jiale Xu Shenghua Gao and Ying Shan. 2024b. FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.09573 (2024)."},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","unstructured":"Kaixin Yao Longwen Zhang Xinhao Yan Yan Zeng Qixuan Zhang Lan Xu Wei Yang Jiayuan Gu and Jingyi Yu. 2025. CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image. ACM Trans. Graph. 44 4 Article 86 (July 2025) 19\u00a0pages. 10.1145\/3730841","DOI":"10.1145\/3730841"},{"key":"e_1_3_3_2_69_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 (2025)."},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_27"},{"key":"e_1_3_3_2_71_1","unstructured":"Bowen Zhang Yiji Cheng Jiaolong Yang Chunyu Wang Feng Zhao Yansong Tang Dong Chen and Baining Guo. 2024b. GaussianCube: Structuring Gaussian Splatting using Optimal Transport for 3D Generative Modeling. arxiv:https:\/\/arXiv.org\/abs\/2403.19655\u00a0[cs.CV]"},{"key":"e_1_3_3_2_72_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 Trans. Graph. 42 4 Article 92 (jul 2023) 16\u00a0pages. 10.1145\/3592442","DOI":"10.1145\/3592442"},{"key":"e_1_3_3_2_73_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang Junyi","year":"2025","unstructured":"Junyi Zhang, Charles Herrmann, Junhwa Hur, Varun Jampani, Trevor Darrell, Forrester Cole, Deqing Sun, and Ming-Hsuan Yang. 2025. MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=lJpqxFgWCM"},{"key":"e_1_3_3_2_74_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. 2024c. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201320.","DOI":"10.1145\/3658146"},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14602"},{"key":"e_1_3_3_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00799"}],"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":"2026-07-16T18:14:12Z","timestamp":1784225652000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":76,"alternative-id":["10.1145\/3799902.3811152","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811152","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"}}]}}