{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:20:21Z","timestamp":1773415221683,"version":"3.50.1"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73397-0_10","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:07:23Z","timestamp":1730574443000},"page":"162-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":115,"title":["Gaussian Grouping: Segment and\u00a0Edit Anything in\u00a03D Scenes"],"prefix":"10.1007","author":[{"given":"Mingqiao","family":"Ye","sequence":"first","affiliation":[]},{"given":"Martin","family":"Danelljan","sequence":"additional","affiliation":[]},{"given":"Fisher","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Ke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-nerf 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR4","unstructured":"Cen, J., et al.: Segment anything in 3d with nerfs. In: NeurIPS (2023)"},{"key":"10_CR5","unstructured":"Chen, X., Tang, J., Wan, D., Wang, J., Zeng, G.: Interactive segment anything nerf with feature imitation. arXiv preprint arXiv:2305.16233 (2023)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3d using gaussian splatting. arXiv preprint arXiv:2309.16585 (2023)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Oh, S.W., Price, B., Schwing, A., Lee, J.Y.: Tracking anything with decoupled video segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"10_CR9","unstructured":"Dou, B., Zhang, T., Ma, Y., Wang, Z., Yuan, Z.: Cosseggaussians: compact and swift scene segmenting 3d gaussians with dual feature fusion. arXiv preprint arXiv:2401.05925 (2024)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Fu, X., Zhang, S., Chen, T., Lu, Y., Zhu, L., Zhou, X., Geiger, A., Liao, Y.: Panoptic nerf: 3d-to-2d label transfer for panoptic urban scene segmentation. In: International Conference on 3D Vision (3DV) (2022)","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A., Holynski, A., Kanazawa, A.: Instruct-nerf2nerf: Editing 3d scenes with instructions. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Kania, K., Yi, K.M., Kowalski, M., Trzci\u0144ski, T., Tagliasacchi, A.: CoNeRF: controllable neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01807"},{"key":"10_CR13","unstructured":"Ke, L., et al.: Segment anything in high quality. In: NeurIPS (2023)"},{"issue":"4","key":"10_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM TOG 42(4), 1\u201314 (2023)","journal-title":"ACM TOG"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: Lerf: Language embedded radiance fields. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"4","key":"10_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073599","volume":"36","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. (ToG) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10_CR18","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing nerf for editing via feature field distillation. In: NeurIPS (2022)"},{"issue":"6","key":"10_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555497","volume":"41","author":"G Kopanas","year":"2022","unstructured":"Kopanas, G., Leimk\u00fchler, T., Rainer, G., Jambon, C., Drettakis, G.: Neural point catacaustics for novel-view synthesis of reflections. ACM TOG 41(6), 1\u201315 (2022)","journal-title":"ACM TOG"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Kopanas, G., Philip, J., Leimk\u00fchler, T., Drettakis, G.: Point-based neural rendering with per-view optimization. In: Computer Graphics Forum, vol.\u00a040, pp. 29\u201343 (2021)","DOI":"10.1111\/cgf.14339"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Kundu, A., et al.: Panoptic neural fields: a semantic object-aware neural scene representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12871\u201312881 (2022)","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.Y.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Lin, Z.H., Forsyth, D., Huang, J.B., Wang, S.: Climatenerf: extreme weather synthesis in neural radiance field. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00299"},{"key":"10_CR24","unstructured":"Liu, H.K., Shen, I., Chen, B.Y., et\u00a0al.: Nerf-in: Free-form nerf inpainting with rgb-d priors. arXiv preprint arXiv:2206.04901 (2022)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, X., Zhang, Z., Zhang, R., Zhu, J.Y., Russell, B.: Editing conditional radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, B., Huang, J., Tai, Y.W., Tang, C.K.: Instance neural radiance field. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00079"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 (2023)","DOI":"10.1109\/3DV62453.2024.00044"},{"issue":"2","key":"10_CR29","first-page":"99","volume":"1","author":"N Max","year":"1995","unstructured":"Max, N.: Optical models for direct volume rendering. IEEE TVCG 1(2), 99\u2013108 (1995)","journal-title":"IEEE TVCG"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Mazur, K., Sucar, E., Davison, A.J.: Feature-realistic neural fusion for real-time, open set scene understanding. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160800"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph. (TOG) (2019)","DOI":"10.1145\/3306346.3322980"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: Representing scenes as neural radiance fields for view synthesis. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., et al.: Spin-nerf: multiview segmentation and perceptual inpainting with neural radiance fields. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., Kant, Y., Kelly, J., Gilitschenski, I.: Laterf: label and text driven object radiance fields. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20062-5_2"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Ost, J., Mannan, F., Thuerey, N., Knodt, J., Heide, F.: Neural scene graphs for dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C., Tagliasacchi, A., Pollefeys, M., Funkhouser, T., et\u00a0al.: Openscene: 3d scene understanding with open vocabularies. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H.: Langsplat: 3d language gaussian splatting. arXiv preprint arXiv:2312.16084 (2023)","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"10_CR38","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Rebain, D., Jiang, W., Yazdani, S., Li, K., Yi, K.M., Tagliasacchi, A.: Derf: decomposed radiance fields. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01393"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D: mask Transformer for 3D Semantic Instance Segmentation. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"10_CR42","unstructured":"Shen, Q., Yang, X., Wang, X.: Anything-3d: Towards single-view anything reconstruction in the wild. arXiv preprint arXiv:2304.10261 (2023)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3d scene understanding with neural fields. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"10_CR44","unstructured":"Straub, J., et al.: The Replica dataset: A digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with fourier convolutions. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"10_CR46","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: Open-Vocabulary 3D Instance Segmentation. In: NeurIPS (2023)"},{"key":"10_CR47","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural feature fusion fields: 3d distillation of self-supervised 2d image representations. In: International Conference on 3D Vision (3DV). arXiv preprint arXiv:2209.03494 (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"10_CR49","unstructured":"Vora, S., et al.: Nesf: Neural semantic fields for generalizable semantic segmentation of 3d scenes (2021)"},{"key":"10_CR50","unstructured":"Wang, B., Chen, L., Yang, B.: Dm-nerf: 3d scene geometry decomposition and manipulation from 2d images. arXiv preprint arXiv:2208.07227 (2022)"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J.: Clip-nerf: text-and-image driven manipulation of neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528 (2023)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"10_CR53","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Object-compositional neural implicit surfaces. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"10_CR54","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"10_CR55","unstructured":"Yang, Y., Wu, X., He, T., Zhao, H., Liu, X.: Sam3d: Segment anything in 3d scenes. arXiv preprint arXiv:2306.03908 (2023)"},{"key":"10_CR56","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhu, X., Zhang, L.: Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting. arXiv preprint arXiv:2310.10642 (2023)"},{"key":"10_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101 (2023)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"10_CR58","unstructured":"Yi, T., et al.: Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529 (2023)"},{"issue":"6","key":"10_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356513","volume":"38","author":"W Yifan","year":"2019","unstructured":"Yifan, W., Serena, F., Wu, S., \u00d6ztireli, C., Sorkine-Hornung, O.: Differentiable surface splatting for point-based geometry processing. ACM Trans. Graph. (TOG) 38(6), 1\u201314 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR60","unstructured":"Yu, H.X., Guibas, L.J., Wu, J.: Unsupervised discovery of object radiance fields. arXiv preprint arXiv:2107.07905 (2021)"},{"key":"10_CR61","doi-asserted-by":"crossref","unstructured":"Yuan, Y.J., Sun, Y.T., Lai, Y.K., Ma, Y., Jia, R., Gao, L.: Nerf-editing: geometry editing of neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01781"},{"key":"10_CR62","unstructured":"Zhang, C., Han, D., Qiao, Y., Kim, J.U., Bae, S.H., Lee, S., Hong, C.S.: Faster segment anything: Towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"issue":"4","key":"10_CR63","first-page":"1","volume":"40","author":"J Zhang","year":"2021","unstructured":"Zhang, J., et al.: Editable free-viewpoint video using a layered neural representation. ACM Trans. Graph. (TOG) 40(4), 1\u201318 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, X., Kundu, A., Funkhouser, T., Guibas, L., Su, H., Genova, K.: Nerflets: local radiance fields for efficient structure-aware 3d scene representation from 2d supervision. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00800"},{"key":"10_CR65","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"10_CR66","doi-asserted-by":"crossref","unstructured":"Zwicker, M., Pfister, H., Van\u00a0Baar, J., Gross, M.: Surface splatting. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 371\u2013378 (2001)","DOI":"10.1145\/383259.383300"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73397-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:19:56Z","timestamp":1732990796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}