{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:19:40Z","timestamp":1782317980623,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","award":["140D0423C0076"],"award-info":[{"award-number":["140D0423C0076"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657427","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0483-693X","authenticated-orcid":false,"given":"Kaiwen","family":"Jiang","sequence":"first","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2711-2558","authenticated-orcid":false,"given":"Yang","family":"Fu","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6480-3126","authenticated-orcid":false,"given":"Mukund","family":"Varma T","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7070-2845","authenticated-orcid":false,"given":"Yash","family":"Belhe","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3150-778X","authenticated-orcid":false,"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1796-2682","authenticated-orcid":false,"given":"Hao","family":"Su","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3993-5789","authenticated-orcid":false,"given":"Ravi","family":"Ramamoorthi","sequence":"additional","affiliation":[{"name":"University of California, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields. ICCV","author":"Barron T.","year":"2023","unstructured":"Jonathan\u00a0T. Barron, Ben Mildenhall, Dor Verbin, Pratul\u00a0P. Srinivasan, and Peter Hedman. 2023. Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields. ICCV (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Wenjing Bian Zirui Wang Kejie Li Jiawang Bian and Victor\u00a0Adrian Prisacariu. 2023. NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior. CVPR.","DOI":"10.1109\/CVPR52729.2023.00405"},{"key":"e_1_3_2_2_3_1","volume-title":"MiDaS v3.1 \u2013 A Model Zoo for Robust Monocular Relative Depth Estimation. arXiv preprint arXiv:2307.14460","author":"Birkl Reiner","year":"2023","unstructured":"Reiner Birkl, Diana Wofk, and Matthias M\u00fcller. 2023. MiDaS v3.1 \u2013 A Model Zoo for Robust Monocular Relative Depth Estimation. arXiv preprint arXiv:2307.14460 (2023)."},{"key":"e_1_3_2_2_4_1","volume-title":"Plenoptic Sampling. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH \u201900)","author":"Chai Jin-Xiang","year":"2000","unstructured":"Jin-Xiang Chai, Xin Tong, Shing-Chow Chan, and Heung-Yeung Shum. 2000. Plenoptic Sampling. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH \u201900). ACM Press\/Addison-Wesley Publishing Co., USA, 307\u2013318."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/166117.166153"},{"key":"e_1_3_2_2_6_1","volume-title":"Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images. arXiv preprint arXiv:2311.13398","author":"Chung Jaeyoung","year":"2023","unstructured":"Jaeyoung Chung, Jeongtaek Oh, and Kyoung\u00a0Mu Lee. 2023. Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images. arXiv preprint arXiv:2311.13398 (2023)."},{"key":"e_1_3_2_2_7_1","volume-title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Deng Kangle","year":"2022","unstructured":"Kangle Deng, Andrew Liu, Jun-Yan Zhu, and Deva Ramanan. 2022. Depth-supervised NeRF: Fewer Views and Faster Training for Free. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 12872\u201312881."},{"key":"e_1_3_2_2_8_1","volume-title":"COLMAP-Free 3D Gaussian Splatting. arXiv preprint arXiv:2312.07504","author":"Fu Yang","year":"2023","unstructured":"Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei\u00a0A Efros, and Xiaolong Wang. 2023. COLMAP-Free 3D Gaussian Splatting. arXiv preprint arXiv:2312.07504 (2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237200"},{"key":"e_1_3_2_2_10_1","volume-title":"SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. arXiv preprint arXiv:2311.12775","author":"Gu\u00e9don Antoine","year":"2023","unstructured":"Antoine Gu\u00e9don and Vincent Lepetit. 2023. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. arXiv preprint arXiv:2311.12775 (2023)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201384"},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning. PMLR, 13000\u201313016","author":"Heo Hwan","year":"2023","unstructured":"Hwan Heo, Taekyung Kim, Jiyoung Lee, Jaewon Lee, Soohyun Kim, Hyunwoo\u00a0J Kim, and Jin-Hwa Kim. 2023. Robust camera pose refinement for multi-resolution hash encoding. In International Conference on Machine Learning. PMLR, 13000\u201313016."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980251"},{"key":"e_1_3_2_2_14_1","unstructured":"Bingxin Ke Anton Obukhov Shengyu Huang Nando Metzger Rodrigo\u00a0Caye Daudt and Konrad Schindler. 2023. Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation. arxiv:2312.02145\u00a0[cs.CV]"},{"key":"e_1_3_2_2_15_1","volume-title":"Track & Map 3D Gaussians for Dense RGB-D SLAM. arXiv preprint","author":"Keetha Nikhil","year":"2023","unstructured":"Nikhil Keetha, Jay Karhade, Krishna\u00a0Murthy Jatavallabhula, Gengshan Yang, Sebastian Scherer, Deva Ramanan, and Jonathon Luiten. 2023. SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM. arXiv preprint (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_17_1","volume-title":"InfoNeRF: Ray Entropy Minimization for Few-Shot Neural","volume":"2022","author":"Kim Mijeong","year":"2022","unstructured":"Mijeong Kim, Seonguk Seo, and Bohyung Han. 2022. InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 12902\u201312911."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_3_2_2_19_1","volume-title":"Robust Consistent Video Depth Estimation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Kopf Johannes","year":"2021","unstructured":"Johannes Kopf, Xuejian Rong, and Jia-Bin Huang. 2021. Robust Consistent Video Depth Estimation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00149"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0152-6"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237199"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218398"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00629"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Andreas Meuleman Yu-Lun Liu Chen Gao Jia-Bin Huang Changil Kim Min\u00a0H. Kim and Johannes Kopf. 2023. Progressively Optimized Local Radiance Fields for Robust View Synthesis. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01587"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P. Srinivasan Matthew Tancik Jonathan\u00a0T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618321"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_2_2_34_1","volume-title":"Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501 (2020)."},{"key":"e_1_3_2_2_35_1","volume-title":"Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Sch\u00f6nberger Johannes\u00a0Lutz","year":"2016","unstructured":"Johannes\u00a0Lutz Sch\u00f6nberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_36_1","volume-title":"Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV).","author":"Sch\u00f6nberger Johannes\u00a0Lutz","year":"2016","unstructured":"Johannes\u00a0Lutz Sch\u00f6nberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0107-3"},{"key":"e_1_3_2_2_38_1","volume-title":"LoFTR: Detector-Free Local Feature Matching with Transformers. CVPR","author":"Sun Jiaming","year":"2021","unstructured":"Jiaming Sun, Zehong Shen, Yuang Wang, Hujun Bao, and Xiaowei Zhou. 2021. LoFTR: Detector-Free Local Feature Matching with Transformers. CVPR (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"QuadTree Attention for Vision Transformers. ICLR","author":"Tang Shitao","year":"2022","unstructured":"Shitao Tang, Jiahui Zhang, Siyu Zhu, and Ping Tan. 2022. QuadTree Attention for Vision Transformers. ICLR (2022)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings, Part II 16","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16. Springer, 402\u2013419."},{"key":"e_1_3_2_2_41_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Varma T","year":"2023","unstructured":"Mukund\u00a0T Varma, Peihao Wang, Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, and Zhangyang Wang. 2023. Is Attention All That NeRF Needs?. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_42_1","volume-title":"SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis. IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang Guangcong","year":"2023","unstructured":"Guangcong Wang, Zhaoxi Chen, Chen\u00a0Change Loy, and Ziwei Liu. 2023. SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis. IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)."},{"key":"e_1_3_2_2_43_1","volume-title":"NeRF \u2212 \u2212: Neural Radiance Fields Without Known Camera Parameters. arXiv preprint arXiv:2102.07064","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor\u00a0Adrian Prisacariu. 2021. NeRF \u2212 \u2212: Neural Radiance Fields Without Known Camera Parameters. arXiv preprint arXiv:2102.07064 (2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618369"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555479"},{"key":"e_1_3_2_2_46_1","volume-title":"SparseGS: Real-Time 360\u00b0 Sparse View Synthesis using Gaussian Splatting. Arxiv","author":"Xiong Haolin","year":"2023","unstructured":"Haolin Xiong, Sairisheek Muttukuru, Rishi Upadhyay, Pradyumna Chari, and Achuta Kadambi. 2023. SparseGS: Real-Time 360\u00b0 Sparse View Synthesis using Gaussian Splatting. Arxiv (2023)."},{"key":"e_1_3_2_2_47_1","volume-title":"GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting. arXiv preprint arXiv:2311.11700","author":"Yan Chi","year":"2023","unstructured":"Chi Yan, Delin Qu, Dong Wang, Dan Xu, Zhigang Wang, Bin Zhao, and Xuelong Li. 2023. GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting. arXiv preprint arXiv:2311.11700 (2023)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_2_49_1","unstructured":"Qihang Yu Ju He Xueqing Deng Xiaohui Shen and Liang-Chieh Chen. 2023. Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP. In NeurIPS."},{"key":"e_1_3_2_2_50_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems","author":"Yu Zehao","year":"2022","unstructured":"Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, and Andreas Geiger. 2022. MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, Danielle Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.)."},{"key":"e_1_3_2_2_51_1","volume-title":"FSGS: Real-Time Few-Shot View Synthesis using Gaussian Splatting. arxiv:2312.00451\u00a0[cs.CV]","author":"Zhu Zehao","year":"2023","unstructured":"Zehao Zhu, Zhiwen Fan, Yifan Jiang, and Zhangyang Wang. 2023. FSGS: Real-Time Few-Shot View Synthesis using Gaussian Splatting. arxiv:2312.00451\u00a0[cs.CV]"},{"key":"e_1_3_2_2_52_1","volume-title":"Surface Splatting. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH \u201901)","author":"Zwicker Matthias","year":"2001","unstructured":"Matthias Zwicker, Hanspeter Pfister, Jeroen van Baar, and Markus Gross. 2001. Surface Splatting. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH \u201901). Association for Computing Machinery, New York, NY, USA, 371\u2013378."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2002.1021576"}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657427","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:36Z","timestamp":1750295376000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":53,"alternative-id":["10.1145\/3641519.3657427","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657427","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}