{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:38:10Z","timestamp":1770917890095,"version":"3.50.1"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726699","type":"print"},{"value":"9783031726705","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72670-5_26","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"456-472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["FlashSplat: 2D to\u00a03D Gaussian Splatting Segmentation Solved Optimally"],"prefix":"10.1007","author":[{"given":"Qiuhong","family":"Shen","sequence":"first","affiliation":[]},{"given":"Xingyi","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0057-1404","authenticated-orcid":false,"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"26_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":"26_CR2","unstructured":"Bing, W., Chen, L., Yang, B.: DM-NeRF: 3D scene geometry decomposition and manipulation from 2D images (2022). arXiv preprint arXiv:2208.07227"},{"key":"26_CR3","unstructured":"Cen, J., et al.: Segment any 3D gaussians (2023). arXiv preprint arXiv:2312.00860"},{"key":"26_CR4","unstructured":"Cen, J., et al.: Segment anything in 3D with NeRFs. In: NeurIPS (2023)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"26_CR6","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3D using gaussian splatting (2023). arXiv preprint arXiv:2309.16585"},{"key":"26_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1316\u20131326 (2023)","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Fang, J., et al.: Fast dynamic radiance fields with time-aware neural voxels. In: SIGGRAPH Asia (2022)","DOI":"10.1145\/3550469.3555383"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Fei, B., Xu, J., Zhang, R., Zhou, Q., Yang, W., He, Y.: 3D gaussian as a new vision era: A survey (2024). arXiv preprint arXiv:2402.07181","DOI":"10.1109\/TVCG.2024.3397828"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Panoptic NeRF: 3D-to-2D label transfer for panoptic urban scene segmentation. In: 3DV (2022)","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Goel, R., Sirikonda, D., Saini, S., Narayanan, P.: Interactive segmentation of radiance fields (2022). arXiv preprint arXiv:2212.13545","DOI":"10.1109\/CVPR52729.2023.00409"},{"key":"26_CR13","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":"26_CR14","doi-asserted-by":"crossref","unstructured":"Hedman, P., Srinivasan, P.P., Mildenhall, B., Barron, J.T., Debevec, P.E.: Baking neural radiance fields for real-time view synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"26_CR15","unstructured":"Hu, B., Huang, J., Liu, Y., Tai, Y.W., Tang, C.K.: Instance neural radiance field (2023). arXiv preprint arXiv:2304.04395"},{"key":"26_CR16","unstructured":"Hu, X., et al.: Semantic anything in 3D gaussians (2024). arXiv preprint arXiv:2401.17857"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (ToG) 42(4), 1\u201314 (2023)","DOI":"10.1145\/3592433"},{"issue":"4","key":"26_CR18","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":"26_CR19","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: Language embedded radiance fields (2023). arXiv preprint arXiv:2303.09553","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"26_CR20","unstructured":"Kirillov, A., et\u00a0al.: Segment anything (2023). arXiv preprint arXiv:2304.02643"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. 36(4), 1\u201313 (2017)","DOI":"10.1145\/3072959.3073599"},{"key":"26_CR22","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing NeRF for editing via feature field distillation. In: NeurIPS (2022)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Lindell, D.B., Martel, J.N.P., Wetzstein, G.: AutoInt: automatic integration for fast neural volume rendering. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01432"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Ling, H., Kim, S.W., Torralba, A., Fidler, S., Kreis, K.: Align your gaussians: Text-to-4D with dynamic 3D gaussians and composed diffusion models (2023). arXiv preprint arXiv:2312.13763","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"26_CR26","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection (2023). arXiv preprint arXiv:2303.05499"},{"key":"26_CR27","unstructured":"Liu, X., Chen, J., Yu, H., Tai, Y., Tang, C.: Unsupervised multi-view object segmentation using radiance field propagation. In: NeurIPS (2022)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3D gaussians: Tracking by persistent dynamic view synthesis (2023). arXiv preprint arXiv:2308.09713","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph. 38(4), 1\u201314 (2019)","DOI":"10.1145\/3306346.3322980"},{"key":"26_CR30","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":"26_CR31","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":"26_CR32","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 1\u201315 (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Qiu, J., Yang, Y., Wang, X., Tao, D.: Scene essence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8322\u20138333 (2021)","DOI":"10.1109\/CVPR46437.2021.00822"},{"key":"26_CR35","unstructured":"Ren, J., et al.: DreamGaussian4D: Generative 4D gaussian splatting (2023). arXiv preprint arXiv:2312.17142"},{"key":"26_CR36","unstructured":"Ren, J., et\u00a0al.: L4GM: Large 4D gaussian reconstruction model (2024). arXiv preprint arXiv:2406.10324"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Ren, Z., Agarwala, A., Russell, B.C., Schwing, A.G., Wang, O.: Neural volumetric object selection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00604"},{"key":"26_CR38","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR39","unstructured":"Shen, Q., Yang, X., Wang, X.: Anything-3D: Towards single-view anything reconstruction in the wild (2023). arXiv preprint arXiv:2304.10261"},{"key":"26_CR40","unstructured":"Shen, Q., et al.: Gamba: marry gaussian splatting with mamba for single view 3D reconstruction (2024). arXiv preprint arXiv:2403.18795"},{"key":"26_CR41","unstructured":"Stelzner, K., Kersting, K., Kosiorek, A.R.: Decomposing 3D scenes into objects via unsupervised volume segmentation (2021). arXiv preprint arXiv:2104.01148"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"26_CR43","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":"26_CR44","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: Generative gaussian splatting for efficient 3D content creation (2023). arXiv preprint arXiv:2309.16653"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Tang, S., Pei, W., Tao, X., Jia, T., Lu, G., Tai, Y.W.: Scene-generalizable interactive segmentation of radiance fields. In: ACMMM (2023)","DOI":"10.1145\/3581783.3612246"},{"key":"26_CR46","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: 3DV (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"26_CR47","unstructured":"Vora, S., et al.: NeSF: Neural semantic fields for generalizable semantic segmentation of 3D scenes (2021). arXiv preprint arXiv:2111.13260"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Wizadwongsa, S., Phongthawee, P., Yenphraphai, J., Suwajanakorn, S.: NeX: real-time view synthesis with neural basis expansion. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zhou, P., Yi, X., Yuan, X., Zhang, H.: Consistent3D: towards consistent high-fidelity text-to-3D generation with deterministic sampling prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9892\u20139902 (2024)","DOI":"10.1109\/CVPR52733.2024.00944"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, X.: Hash3D: Training-free acceleration for 3D generation (2024). arXiv preprint arXiv:2404.06091","DOI":"10.36227\/techrxiv.171208938.83786646\/v1"},{"key":"26_CR51","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhu, X., Zhang, L.: Real-time photorealistic dynamic scene representation and rendering with 4D gaussian splatting (2023). arXiv preprint arXiv:2310.10642"},{"key":"26_CR52","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 (2023). arXiv preprint arXiv:2309.13101","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"26_CR53","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: Segment and edit anything in 3D scenes (2023). arXiv preprint arXiv:2312.00732"},{"key":"26_CR54","unstructured":"Yi, T., et al.: GaussianDreamer: Fast generation from text to 3D gaussian splatting with point cloud priors (2023). arXiv preprint arXiv:2310.08529"},{"key":"26_CR55","unstructured":"Yi, X., et al.: MVGamba: Unify 3D content generation as state space sequence modeling (2024). arXiv preprint arXiv:2406.06367"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Yi, X., Wu, Z., Xu, Q., Zhou, P., Lim, J.H., Zhang, H.: Diffusion time-step curriculum for one image to 3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9948\u20139958 (2024)","DOI":"10.1109\/CVPR52733.2024.00949"},{"key":"26_CR57","unstructured":"Yin, Y., Xu, D., Wang, Z., Zhao, Y., Wei, Y.: 4DGEN: Grounded 4D content generation with spatial-temporal consistency (2023). arXiv preprint arXiv:2312.17225"},{"key":"26_CR58","unstructured":"Yu, H., Guibas, L.J., Wu, J.: Unsupervised discovery of object radiance fields. In: ICLR (2022)"},{"key":"26_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"26_CR60","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":"26_CR61","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., et al.: Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10324\u201310335 (2024)","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/978-3-031-72670-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:24:33Z","timestamp":1727594673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72670-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726699","9783031726705"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72670-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}