{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T04:47:45Z","timestamp":1769834865047,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Jiangsu Natural Science Foundation","award":["BK20221441"],"award-info":[{"award-number":["BK20221441"]}]},{"name":"Science and Technology Innovation 2030 New Generation Artificial Intelligence Major Project","award":["2021ZD0113303"],"award-info":[{"award-number":["2021ZD0113303"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192783; 62276128; 62106100"],"award-info":[{"award-number":["62192783; 62276128; 62106100"]}],"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613769","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"2180-2188","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5298-7087","authenticated-orcid":false,"given":"Yanqi","family":"Bao","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8334-0486","authenticated-orcid":false,"given":"Yuxin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8504-455X","authenticated-orcid":false,"given":"Jing","family":"Huo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-4330","authenticated-orcid":false,"given":"Tianyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4707-2314","authenticated-orcid":false,"given":"Xinyue","family":"Liang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-7124","authenticated-orcid":false,"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01476"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00782"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-6453-2_10"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237191"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00247"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980251"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","volume-title":"View-Former: NeRF-free Neural Rendering from Few Images Using Transformers. arXiv preprint arXiv:2203.10157","author":"Derner Erik","year":"2022","unstructured":"Jon\u00e1? Kulh\u00e1nek, Erik Derner, Torsten Sattler, and Robert Babu?ka. 2022. View-Former: NeRF-free Neural Rendering from Few Images Using Transformers. arXiv preprint arXiv:2203.10157 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751","author":"Lombardi Stephen","year":"2019","unstructured":"Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, and Yaser Sheikh. 2019. Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Lookingood: Enhancing performance capture with real-time neural re-rendering. arXiv preprint arXiv:1811.05029","author":"Martin-Brualla Ricardo","year":"2018","unstructured":"Ricardo Martin-Brualla, Rohit Pandey, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Julien Valentin, Sameh Khamis, Philip Davidson, Anastasia Tkach, Peter Lincoln, et al. 2018. Lookingood: Enhancing performance capture with real-time neural re-rendering. arXiv preprint arXiv:1811.05029 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00704"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"e_1_3_2_1_21_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130855"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"e_1_3_2_1_24_1","volume-title":"NeRF-SLAM: Real-Dense Monocular SLAM with Neural Radiance Fields. arXiv preprint arXiv:2210.13641","author":"Rosinol Antoni","year":"2022","unstructured":"Antoni Rosinol, John J Leonard, and Luca Carlone. 2022. NeRF-SLAM: Real-Dense Monocular SLAM with Neural Radiance Fields. arXiv preprint arXiv:2210.13641 (2022)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_10"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_20"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"e_1_3_2_1_31_1","unstructured":"Peihao Wang Xuxi Chen Tianlong Chen Subhashini Venugopalan Zhangyang Wang et al. 2022. Is Attention All NeRF Needs? arXiv preprint arXiv:2207.13298 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"e_1_3_2_1_33_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"e_1_3_2_1_35_1","volume-title":"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image. arXiv preprint arXiv:2204.00928","author":"Xu Dejia","year":"2022","unstructured":"Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, and Zhangyang Wang. 2022. SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image. arXiv preprint arXiv:2204.00928 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5336--5345","author":"Yoon Jae Shin","year":"2020","unstructured":"Jae Shin Yoon, Kihwan Kim, Orazio Gallo, Hyun Soo Park, and Jan Kautz. 2020. Novel view synthesis of dynamic scenes with globally coherent depths from a monocular camera. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5336--5345."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_39_1","volume-title":"Region mutual information loss for semantic segmentation. Advances in Neural Information Processing Systems 32","author":"Zhao Shuai","year":"2019","unstructured":"Shuai Zhao, Yang Wang, Zheng Yang, and Deng Cai. 2019. Region mutual information loss for semantic segmentation. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_40_1","volume-title":"Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817","author":"Zhou Tinghui","year":"2018","unstructured":"Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)."},{"key":"e_1_3_2_1_41_1","unstructured":"Xiaojin Jerry Zhu. 2005. Semi-supervised learning literature survey. (2005)."},{"key":"e_1_3_2_1_42_1","volume-title":"Matthew Uyttendaele, Simon Winder, and Richard Szeliski.","author":"Zitnick C Lawrence","year":"2004","unstructured":"C Lawrence Zitnick, Sing Bing Kang, Matthew Uyttendaele, Simon Winder, and Richard Szeliski. 2004. High-quality video view interpolation using a layered representation. ACM transactions on graphics (TOG) 23, 3 (2004), 600--608."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613769","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:04:49Z","timestamp":1755821089000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":42,"alternative-id":["10.1145\/3581783.3613769","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613769","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}