{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:13Z","timestamp":1780392313921,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":51,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612246","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"6744-6755","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Scene-Generalizable Interactive Segmentation of Radiance Fields"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9449-5848","authenticated-orcid":false,"given":"Songlin","family":"Tang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8117-2696","authenticated-orcid":false,"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9126-4746","authenticated-orcid":false,"given":"Xin","family":"Tao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3699-3966","authenticated-orcid":false,"given":"Tanghui","family":"Jia","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-2634","authenticated-orcid":false,"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies & Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-0380","authenticated-orcid":false,"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[{"name":"Dartmouth College, Hanover, NH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings eighth IEEE international conference on computer vision. ICCV","volume":"1","author":"Boykov Yuri Y","year":"2001","unstructured":"Yuri Y Boykov and M-P Jolly. 2001. Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. In Proceedings eighth IEEE international conference on computer vision. ICCV 2001, Vol. 1. IEEE, 105--112."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","volume-title":"Tel Aviv","author":"Chen Anpei","year":"2022","unstructured":"Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, and Hao Su. 2022. Tensorf: Tensorial radiance fields. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXII. Springer, 333--350."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00725"},{"key":"e_1_3_2_1_7_1","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016: 19th International Conference","author":"\u00d6zg\u00fcn","year":"2016","unstructured":"\u00d6zg\u00fcn \u00c7i\u00e7;ek, Ahmed Abdulkadir, Soeren S Lienkamp, Thomas Brox, and Olaf Ronneberger. 2016. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer, 424--432."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_3_2_1_9_1","volume-title":"Interactive Segmentation of Radiance Fields. arXiv preprint arXiv:2212.13545","author":"Goel Rahul","year":"2022","unstructured":"Rahul Goel, Dhawal Sirikonda, Saurabh Saini, and PJ Narayanan. 2022. Interactive Segmentation of Radiance Fields. arXiv preprint arXiv:2212.13545 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"NeRF-RPN: A general framework for object detection in NeRFs. arXiv preprint arXiv:2211.11646","author":"Hu Benran","year":"2022","unstructured":"Benran Hu, Junkai Huang, Yichen Liu, Yu-Wing Tai, and Chi-Keung Tang. 2022. NeRF-RPN: A general framework for object detection in NeRFs. arXiv preprint arXiv:2211.11646 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585499"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00544"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"e_1_3_2_1_14_1","volume-title":"Ken Goldberg, Angjoo Kanazawa, and Matthew Tancik.","author":"Kerr Justin","year":"2023","unstructured":"Justin Kerr, Chung Min Kim, Ken Goldberg, Angjoo Kanazawa, and Matthew Tancik. 2023. LERF: Language Embedded Radiance Fields. arXiv preprint arXiv:2303.09553 (2023)."},{"key":"e_1_3_2_1_15_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_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_3_2_1_17_1","first-page":"23311","article-title":"Decomposing nerf for editing via feature field distillation","volume":"35","author":"Kobayashi Sosuke","year":"2022","unstructured":"Sosuke Kobayashi, Eiichi Matsumoto, and Vincent Sitzmann. 2022. Decomposing nerf for editing via feature field distillation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23311--23330.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"e_1_3_2_1_19_1","volume-title":"Language-driven Semantic Segmentation. arXiv preprint arXiv:2201.03546","author":"Li Boyi","year":"2022","unstructured":"Boyi Li, Kilian Q Weinberger, Serge Belongie, Vladlen Koltun, and Ren\u00e9 Ranftl. 2022. Language-driven Semantic Segmentation. arXiv preprint arXiv:2201.03546 (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00266"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_3_2_1_23_1","volume-title":"Tel Aviv","author":"Liu Qin","year":"2022","unstructured":"Qin Liu, Meng Zheng, Benjamin Planche, Srikrishna Karanam, Terrence Chen, Marc Niethammer, and Ziyan Wu. 2022. PseudoClick: Interactive image segmentation with click imitation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part VI. Springer, 728--745."},{"key":"e_1_3_2_1_24_1","volume-title":"Paddleseg: A high-efficient development toolkit for image segmentation. arXiv preprint arXiv:2101.06175","author":"Liu Yi","year":"2021","unstructured":"Yi Liu, Lutao Chu, Guowei Chen, Zewu Wu, Zeyu Chen, Baohua Lai, and Yuying Hao. 2021. Paddleseg: A high-efficient development toolkit for image segmentation. arXiv preprint arXiv:2101.06175 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01571"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_1_32_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00604"},{"key":"e_1_3_2_1_35_1","volume-title":"ACM transactions on graphics (TOG)","author":"Rother Carsten","year":"2004","unstructured":"Carsten Rother, Vladimir Kolmogorov, and Andrew Blake. 2004. \"GrabCut\" interactive foreground extraction using iterated graph cuts. ACM transactions on graphics (TOG), Vol. 23, 3 (2004), 309--314."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710815"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"e_1_3_2_1_41_1","volume-title":"Etienne Pot, Andrea Tagliasacchi, and Daniel Duckworth.","author":"Vora Suhani","year":"2021","unstructured":"Suhani Vora, Noha Radwan, Klaus Greff, Henning Meyer, Kyle Genova, Mehdi SM Sajjadi, Etienne Pot, Andrea Tagliasacchi, and Daniel Duckworth. 2021. Nesf: Neural semantic fields for generalizable semantic segmentation of 3d scenes. arXiv preprint arXiv:2111.13260 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Neus: Learning neural implicit surfaces by","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)."},{"key":"e_1_3_2_1_43_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, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"e_1_3_2_1_47_1","volume-title":"BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. arXiv preprint arXiv:2302.14859","author":"Yariv Lior","year":"2023","unstructured":"Lior Yariv, Peter Hedman, Christian Reiser, Dor Verbin, Pratul P Srinivasan, Richard Szeliski, Jonathan T Barron, and Ben Mildenhall. 2023. BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. arXiv preprint arXiv:2302.14859 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01225"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"}],"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\/3581783.3612246","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:31Z","timestamp":1755820711000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":51,"alternative-id":["10.1145\/3581783.3612246","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612246","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"}}]}}