{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:35:30Z","timestamp":1790562930083,"version":"4.1.0"},"publisher-location":"Cham","reference-count":120,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368386","type":"print"},{"value":"9783032368393","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-36839-3_16","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:31:54Z","timestamp":1789317114000},"page":"271-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["One Video, One World: Turning Monocular Video into\u00a0Physical 4D Scenes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4195-3766","authenticated-orcid":false,"given":"Junhao","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0708-1659","authenticated-orcid":false,"given":"Boran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4979-6307","authenticated-orcid":false,"given":"Mingjin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2714-2092","authenticated-orcid":false,"given":"Henghaofan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4983-8478","authenticated-orcid":false,"given":"Saining","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5146-222X","authenticated-orcid":false,"given":"Congcong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-581X","authenticated-orcid":false,"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5942-3671","authenticated-orcid":false,"given":"Ruqi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2066-8775","authenticated-orcid":false,"given":"Zhihao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6326-7357","authenticated-orcid":false,"given":"Yufei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"16_CR1","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"issue":"5","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1137\/0916069","volume":"16","author":"RH Byrd","year":"1995","unstructured":"Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comput. 16(5), 1190\u20131208 (1995)","journal-title":"SIAM J. Sci. Comput."},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Cao, A., Johnson, J.: HexPlane: a fast representation for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 130\u2013141 (2023)","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"16_CR4","unstructured":"Cao, Y., et\u00a0al.: Reconstructing 4D spatial intelligence: a survey. arXiv preprint arXiv:2507.21045 (2025)"},{"key":"16_CR5","unstructured":"Cao, Z., Hong, F., Chen, Z., Pan, L., Liu, Z.: PHYSX-anything: simulation-ready physical 3D assets from single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5839\u20135848 (2026)"},{"key":"16_CR6","unstructured":"Carion, N., et\u00a0al.: SAM 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"16_CR7","unstructured":"Chen, H., Chen, X., Xu, Z., Chen, A.: Motion 3-to-4: 3D motion reconstruction for 4D synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28947\u201328958 (2026)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhang, B., Tang, X., Wonka, P.: V2M4: 4D mesh animation reconstruction from a single monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11643\u201311653 (2025)","DOI":"10.1109\/ICCV51701.2025.01083"},{"key":"16_CR9","unstructured":"Chen, J., et al.: DanceTogether: generating interactive multi-person video without identity drifting. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=7VEECFBzmm"},{"key":"16_CR10","unstructured":"Chen, J., et al.: LottieGPT: tokenizing vector animation for autoregressive generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 31639\u201331651 (2026)"},{"key":"16_CR11","unstructured":"Chen, J., Li, X., Ye, X., Li, C., Fan, Z., Zhao, H.: Idea23D: collaborative LMM agents enable 3D model generation from interleaved multimodal inputs. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 4149\u20134166 (2025)"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: LLMsPark: a benchmark for evaluating large language models in strategic gaming contexts. In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 182\u2013194. Association for Computational Linguistics, Suzhou, China (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-emnlp.12, https:\/\/aclanthology.org\/2025.findings-emnlp.12\/","DOI":"10.18653\/v1\/2025.findings-emnlp.12"},{"key":"16_CR13","unstructured":"Chen, M., et al.: HVG-3D: bridging real and simulation domains for 3D-conditional hand-object interaction video synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15986\u201315997 (2026)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Chen, M., Chen, J., Gao, H.a., Chen, X., Fan, Z., Zhao, H.: Ultraman: ultra-fast and high-resolution texture generation for 3D human reconstruction from a single image. Mach. Vis. Appl. 37(2), 24 (2026)","DOI":"10.1007\/s00138-025-01782-w"},{"key":"16_CR15","unstructured":"Chen, M., Wang, L., Ao, S., Zhang, Y., Xu, K., Guo, Y.: Layout2Scene: 3D semantic layout guided scene generation via geometry and appearance diffusion priors (2025). https:\/\/arxiv.org\/abs\/2501.02519"},{"key":"16_CR16","doi-asserted-by":"publisher","unstructured":"Chen, M., Yang, R., Hu, Q., Xue, K., Zhou, S., Guo, Y.: Graph2Scene: versatile 3D indoor scene generation with interaction-aware scene graph. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 11313\u201311320 (2025). https:\/\/doi.org\/10.1109\/IROS60139.2025.11246595","DOI":"10.1109\/IROS60139.2025.11246595"},{"key":"16_CR17","unstructured":"Chen, W., Rao, J., Wang, W., Li, X., Cheng, X., Cao, L.: CustomTex: high-fidelity indoor scene texturing via multi-reference customization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4280\u20134290 (2026)"},{"key":"16_CR18","doi-asserted-by":"publisher","first-page":"96181","DOI":"10.52202\/079017-3048","volume":"37","author":"WH Chu","year":"2024","unstructured":"Chu, W.H., Ke, L., Fragkiadaki, K.: DreamScene4D: dynamic multi-object scene generation from monocular videos. Adv. Neural. Inf. Process. Syst. 37, 96181\u201396206 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR19","unstructured":"Coumans, E., Bai, Y.: Pybullet, a Python module for physics simulation for games, robotics and machine learning. https:\/\/pybullet.org\/wordpress\/ (2016\u20132021)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Dille, S., Careaga, C., Aksoy, Y.: Intrinsic single-image HDR reconstruction. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 161\u2013177. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-73247-8_10","DOI":"10.1007\/978-3-031-73247-8_10"},{"key":"16_CR22","unstructured":"Edstedt, J., et al.: Roma V2: harder better faster denser feature matching. arXiv preprint arXiv:2511.15706 (2025)"},{"issue":"6","key":"16_CR23","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Meanti, G., Warburg, F.R., Recht, B., Kanazawa, A.: K-planes: explicit radiance fields in space, time, and appearance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12479\u201312488 (2023)","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"16_CR25","unstructured":"Geng, Z., et al.: One view, many worlds: single-image to 3D object meets generative domain randomization for one-shot 6D pose estimation. In: 9th Annual Conference on Robot Learning (2025). https:\/\/openreview.net\/forum?id=kto4zVmo4w"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: ArtiScene: language-driven artistic 3D scene generation through image intermediary. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2891\u20132901 (2025)","DOI":"10.1109\/CVPR52734.2025.00275"},{"key":"16_CR27","doi-asserted-by":"publisher","unstructured":"Guo, H., et al.: IW-bench: evaluating large multimodal models for converting image-to-web. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 6449\u20136466. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.334, https:\/\/aclanthology.org\/2025.findings-acl.334\/","DOI":"10.18653\/v1\/2025.findings-acl.334"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Guo, J., et\u00a0al.: Auto-connect: connectivity-preserving RigFormer with direct preference optimization. arXiv preprint arXiv:2506.11430 (2025)","DOI":"10.52202\/085713-2913"},{"key":"16_CR29","unstructured":"Guo, Z., Zhang, O., Xiang, J., Zhao, A., Zhou, W., Li, H.: Make-it-poseable: feed-forward latent posing model for 3D humanoid character animation. arXiv preprint arXiv:2512.16767 (2025)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Han, H., et al.: REPARO: compositional 3D assets generation with differentiable 3D layout alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25367\u201325377 (2025)","DOI":"10.1109\/ICCV51701.2025.02353"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Hu, S., Arroyo, D.M., Debats, S., Manhardt, F., Carlone, L., Tombari, F.: Mixed diffusion for 3D indoor scene synthesis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1262\u20131272 (2026)","DOI":"10.1109\/WACV61042.2026.00129"},{"issue":"6","key":"16_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3763343","volume":"44","author":"Y Hu","year":"2025","unstructured":"Hu, Y., et al.: SPLIT4D: decomposed 4D scene reconstruction without video segmentation. ACM Trans. Graph. (TOG) 44(6), 1\u201315 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Huang, J., Gojcic, Z., Atzmon, M., Litany, O., Fidler, S., Williams, F.: Neural kernel surface reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4369\u20134379 (2023)","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: MIDI: multi-instance diffusion for single image to 3D scene generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23646\u201323657 (2025)","DOI":"10.1109\/CVPR52734.2025.02202"},{"key":"16_CR35","unstructured":"Jiang, Z., Zheng, C., Laina, I., Larlus, D., Vedaldi, A.: Mesh4D: 4D mesh reconstruction and tracking from monocular video. arXiv preprint arXiv:2601.05251 (2026)"},{"key":"16_CR36","unstructured":"Karhade, J., et al.: ANY4D: unified feed-forward metric 4D reconstruction. arXiv preprint arXiv:2512.10935 (2025)"},{"issue":"4","key":"16_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimkuehler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (TOG) 42(4), 1\u201314 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR38","unstructured":"Kong, L., et al.: 3D and 4D world modeling: a survey. arXiv preprint arXiv:2509.07996 (2025)"},{"key":"16_CR39","unstructured":"Black Forest Labs: FLUX.2: frontier visual intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2"},{"issue":"2","key":"16_CR40","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EP N P: an accurate O (N) solution to the P N P problem. Int. J. Comput. Vis. 81(2), 155\u2013166 (2009)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6498\u20136508 (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Y., Zheng, H., Luo, Y., Wen, B.: Sparc3D: sparse representation and construction for high-resolution 3D shapes modeling. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2026). https:\/\/openreview.net\/forum?id=yslRXs9gcJ","DOI":"10.52202\/085713-3956"},{"key":"16_CR43","doi-asserted-by":"publisher","first-page":"21377","DOI":"10.52202\/079017-0674","volume":"37","author":"Z Li","year":"2024","unstructured":"Li, Z., Chen, Y., Liu, P.: Dreammesh4D: video-to-4D generation with sparse-controlled gaussian-mesh hybrid representation. Adv. Neural. Inf. Process. Syst. 37, 21377\u201321400 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Liang, H., Xu, D., Bhatt, N.P., Hu, H., Liang, H., Plataniotis, K.N.: Comp4D: compositional 4D scene generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3567\u20133577 (2026)","DOI":"10.1109\/WACV61042.2026.00348"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Liang, H., et al.: Diffusion4D: fast spatial-temporal consistent 4D generation via video diffusion models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, pp. 110854\u2013110875 (2024)","DOI":"10.52202\/079017-3519"},{"key":"16_CR46","unstructured":"Lin, G., et\u00a0al.: Pat3D: physics-augmented text-to-3D scene generation. arXiv preprint arXiv:2511.21978 (2025)"},{"key":"16_CR47","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, Z., Xu, D., Jiang, S., Gong, Y., Jiang, M.: Phys4DGEN: physics-compliant 4D generation with multi-material composition perception. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 10398\u201310407 (2025)","DOI":"10.1145\/3746027.3755647"},{"key":"16_CR49","unstructured":"Ling, L., Ge, Y., Sheng, Y., Bera, A.: I-scene: 3D instance models are implicit generalizable spatial learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26974\u201326983 (2026)"},{"key":"16_CR50","unstructured":"Ling, L., et al.: SceneThesis: a language and vision agentic framework for 3D scene generation. arXiv preprint arXiv:2505.02836 (2025)"},{"key":"16_CR51","unstructured":"Liu, I., Su, H., Wang, X.: Dynamic gaussians mesh: consistent mesh reconstruction from dynamic scenes. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=LuGHbK8qTa"},{"issue":"4","key":"16_CR52","first-page":"1","volume":"44","author":"I Liu","year":"2025","unstructured":"Liu, I., et al.: RigAnything: template-free autoregressive rigging for diverse 3D assets. ACM Trans. Graph. (TOG) 44(4), 1\u201312 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Liu, T., et al.: Free4D: tuning-free 4D scene generation with spatial-temporal consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25571\u201325582 (2025)","DOI":"10.1109\/ICCV51701.2025.02372"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3D: single image to 3D using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9970\u20139980 (2024)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (Oct 2015)","DOI":"10.1145\/2816795.2818013"},{"key":"16_CR56","first-page":"148548","volume":"38","author":"Y Lu","year":"2026","unstructured":"Lu, Y., et al.: Orientation matters: making 3D generative models orientation-aligned. Adv. Neural. Inf. Process. Syst. 38, 148548\u2013148583 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR57","unstructured":"Makoviychuk, V., et al.: ISAAC GYM: high performance GPU-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Meng, Y., Wu, H., Zhang, Y., Xie, W.: SceneGEN: single-image 3D scene generation in one feedforward pass. In: Thirteenth International Conference on 3D Vision (2026). https:\/\/openreview.net\/forum?id=KpelxFFxQT","DOI":"10.1109\/3DV69130.2026.00058"},{"key":"16_CR59","unstructured":"Miao, Q., et al.: Advances in 4D generation: a survey. arXiv preprint arXiv:2503.14501 (2025)"},{"key":"16_CR60","unstructured":"Miao, X., Dong, J., Zhao, Q., Yang, Y., Chen, J., Long, Y.: From frames to sequences: temporally consistent human-centric dense prediction (2026). https:\/\/arxiv.org\/abs\/2602.01661"},{"issue":"1","key":"16_CR61","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"16_CR62","unstructured":"Nazarczuk, M., Tanay, T., Moreau, A., Zhang, Z., P\u00e9rez-Pellitero, E.: Charge: a comprehensive novel view synthesis benchmark and dataset to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15323\u201315333 (2026)"},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"issue":"6","key":"16_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480487","volume":"40","author":"K Park","year":"2021","unstructured":"Park, K., et al.: HyperNERF: a higher-dimensional representation for topologically varying neural radiance fields. ACM Trans. Graph. (TOG) 40(6), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NERF: neural radiance fields for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318\u201310327 (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"16_CR66","unstructured":"Qiu, X., et al.: Articulate AnyMesh: open-vocabulary 3D articulated objects modeling. In: 9th Annual Conference on Robot Learning (2025). https:\/\/openreview.net\/forum?id=BNCh3SS1Yl"},{"key":"16_CR67","doi-asserted-by":"publisher","first-page":"56828","DOI":"10.52202\/079017-1810","volume":"37","author":"J Ren","year":"2024","unstructured":"Ren, J., et al.: L4GM: Large 4D gaussian reconstruction model. Adv. Neural. Inf. Process. Syst. 37, 56828\u201356858 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR68","unstructured":"Sabathier, R., Novotny, D., Mitra, N.J., Monnier, T.: Actionmesh: Animated 3d mesh generation with temporal 3d diffusion, (2026). arXiv:2601.16148 arXiv preprint"},{"key":"16_CR69","unstructured":"Shi, Y., et al.: SceneMaker: open-set 3D scene generation with decoupled de-occlusion and pose estimation model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27146\u201327156 (2026)"},{"key":"16_CR70","unstructured":"Siddiqui, Y., et\u00a0al.: Shaper: robust conditional 3D shape generation from casual captures. arXiv preprint arXiv:2601.11514 (2026)"},{"key":"16_CR71","unstructured":"Singer, U., et al.: Text-to-4D dynamic scene generation. In: Proceedings of the 40th International Conference on Machine Learning, pp. 31915\u201331929 (2023)"},{"key":"16_CR72","first-page":"72152","volume":"38","author":"C Song","year":"2026","unstructured":"Song, C., et al.: Puppeteer: rig and animate your 3D models. Adv. Neural. Inf. Process. Syst. 38, 72152\u201372184 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR73","doi-asserted-by":"crossref","unstructured":"Song, C., et\u00a0al.: MagicArticulate: make your 3D models articulation-ready. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15998\u201316007 (2025)","DOI":"10.1109\/CVPR52734.2025.01491"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: Drive: diffusion-based rigging empowers generation of versatile and expressive characters. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21170\u201321180 (2025)","DOI":"10.1109\/CVPR52734.2025.01972"},{"key":"16_CR75","unstructured":"Sun, M., et al.: Animator-centric skeleton generation on objects with fine-grained details. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17336\u201317345 (2026)"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Tang, X., Li, R., Fan, X.: ZeroScene: a zero-shot framework for 3D scene generation from a single image and controllable texture editing. In: Computer Graphics Forum, p. e70419. Wiley Online Library (2026)","DOI":"10.1111\/cgf.70419"},{"key":"16_CR77","doi-asserted-by":"crossref","unstructured":"Tao, S., Zhou, B., Tu, H., Wang, Y., Liu, Y.: Tesselation GS: neural mesh gaussians for robust monocular reconstruction of dynamic objects. In: Thirteenth International Conference on 3D Vision (2025)","DOI":"10.1109\/3DV69130.2026.00103"},{"key":"16_CR78","unstructured":"Team, S.D., et al.: SAM 3D: 3DFY anything in images (2025). https:\/\/arxiv.org\/abs\/2511.16624"},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MUJOCO: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: FLUX4D: flow-based unsupervised 4D reconstruction. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=FeUGQ6AiKR","DOI":"10.52202\/085713-3529"},{"key":"16_CR82","unstructured":"Wang, L., et al.: SceneTransporter: optimal transport-guided compositional latent diffusion for single-image structured 3D scene generation. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=xjCkwPhQWq"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUST3R: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"16_CR84","unstructured":"Wang, Xet al.: EmbodiedGEN: towards a generative 3D world engine for embodied intelligence. arXiv preprint arXiv:2506.10600 (2025)"},{"key":"16_CR85","unstructured":"Wang, Z., et al.: LLAMA-mesh: Unifying 3D mesh generation with language models. arXiv preprint arXiv:2411.09595 (2024)"},{"key":"16_CR86","unstructured":"Wang, Z., He, Y., Yang, L., Zou, W., Ma, H., Liu, L., Sui, W., Guo, Y., Su, H.: Tabletopgen: Instance-level interactive 3d tabletop scene generation from text or single image, (2025). arXiv:2512.01204 arXiv preprint"},{"key":"16_CR87","unstructured":"Wen, B., Xie, H., Chen, Z., Hong, F., Liu, Z.: 3D scene generation: a survey. arXiv:2505.05474 arXiv preprint (2025)"},{"key":"16_CR88","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: FoundationPose: unified 6D pose estimation and tracking of novel objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17868\u201317879 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"16_CR89","unstructured":"Weng, F., et al.: GarmentGPT: compositional garment pattern generation via discrete latent tokenization. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=XzXKnazRBF"},{"key":"16_CR90","unstructured":"Weng, J., et al.: Feedforward 3D editing learns from semantic-part transformation. arXiv preprint arXiv:2605.27351 (2026)"},{"key":"16_CR91","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D gaussian splatting for real-time dynamic scene rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"16_CR92","doi-asserted-by":"publisher","first-page":"28559","DOI":"10.52202\/068431-2070","volume":"35","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Chen, Z., Liu, S., Ren, Z., Wang, S.: Casa: category-agnostic skeletal animal reconstruction. Adv. Neural. Inf. Process. Syst. 35, 28559\u201328574 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR93","doi-asserted-by":"crossref","unstructured":"Wu, Z., Yu, C., Wang, F., Bai, X.: AnimateAnymesh: a feed-forward 4D foundation model for text-driven universal mesh animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13557\u201313568 (2025)","DOI":"10.1109\/ICCV51701.2025.01259"},{"key":"16_CR94","unstructured":"Xia, H., et\u00a0al.: SAGE: scalable agentic 3D scene generation for embodied AI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22358\u201322368 (2026)"},{"key":"16_CR95","doi-asserted-by":"crossref","unstructured":"Xiang, F., et\u00a0al.: SAPIEN: a simulated part-based interactive environment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11097\u201311107 (2020)","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"16_CR96","unstructured":"Xiang, J., et al.: Native and compact structured latents for 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14419\u201314429 (2026)"},{"key":"16_CR97","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21469\u201321480 (2025)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"16_CR98","unstructured":"Xie, Y., Yao, C.H., Voleti, V., Jiang, H., Jampani, V.: SV4d: dynamic 3D content generation with multi-frame and multi-view consistency. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=tJoS2d0Onf"},{"key":"16_CR99","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhou, Y., Kalogerakis, E., Landreth, C., Singh, K.: RigNet: neural rigging for articulated characters. ACM Trans. Graph. 39(4) (2020)","DOI":"10.1145\/3386569.3392379"},{"key":"16_CR100","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"16_CR101","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything V2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR102","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: InstaScene: towards complete 3D instance decomposition and reconstruction from cluttered scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7771\u20137781 (2025)","DOI":"10.1109\/ICCV51701.2025.00729"},{"issue":"4","key":"16_CR103","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3730841","volume":"44","author":"K Yao","year":"2025","unstructured":"Yao, K., et al.: Cast: component-aligned 3D scene reconstruction from an RGB image. ACM Trans. Graph. (TOG) 44(4), 1\u201319 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR104","doi-asserted-by":"crossref","unstructured":"Yao, Y., Deng, Z., Hou, J.: Riggs: rigging of 3D gaussians for modeling articulated objects in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5592\u20135601 (2025)","DOI":"10.1109\/CVPR52734.2025.00525"},{"key":"16_CR105","doi-asserted-by":"crossref","unstructured":"Ye, C., et al.: Hi3DGEN: high-fidelity 3D geometry generation from images via normal bridging. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25050\u201325061 (2025)","DOI":"10.1109\/ICCV51701.2025.02323"},{"key":"16_CR106","doi-asserted-by":"crossref","unstructured":"Ye, X., et al.: MMAD: multi-modal movie audio description. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 11415\u201311428 (2024)","DOI":"10.63317\/4s5pfq3wxzuq"},{"key":"16_CR107","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: Vision-as-inverse-graphics agent via interleaved multimodal reasoning. arXiv:2601.11109 arXiv preprint (2026)","DOI":"10.1007\/978-3-032-37464-6_30"},{"key":"16_CR108","doi-asserted-by":"crossref","unstructured":"Yunus, R., et al.: Recent trends in 3D reconstruction of general non-rigid scenes. In: Computer Graphics Forum, vol.\u00a043, p. e15062. Wiley Online Library (2024)","DOI":"10.1111\/cgf.15062"},{"key":"16_CR109","doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: ZHUJIU: a multi-dimensional, multi-faceted Chinese benchmark for large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 479\u2013494 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.44"},{"key":"16_CR110","unstructured":"Zhang, H., Chang, D., Li, F., Soleymani, M., Ahuja, N.: Magicpose4D: crafting articulated models with appearance and motion control. Trans. Mach. Learn. Res. 2025 (2025)"},{"issue":"4","key":"16_CR111","first-page":"1","volume":"44","author":"JP Zhang","year":"2025","unstructured":"Zhang, J.P., Pu, C.F., Guo, M.H., Cao, Y.P., Hu, S.M.: One model to rig them all: diverse skeleton rigging with UNIRIG. ACM Trans. Graph. (TOG) 44(4), 1\u201318 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR112","unstructured":"Zhang, J., et al.: MonST3r: a simple approach for estimating geometry in the presence of motion. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=lJpqxFgWCM"},{"issue":"4","key":"16_CR113","first-page":"1","volume":"43","author":"L Zhang","year":"2024","unstructured":"Zhang, L., et al.: Clay: a controllable large-scale generative model for creating high-quality 3D assets. ACM Trans. Graph. (TOG) 43(4), 1\u201320 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR114","unstructured":"Zhang, Y., Wang, Y., Zhang, Z., Tang, H.: Code2Worlds: empowering coding LLMS for 4D world generation. arXiv preprint arXiv:2602.11757 (2026)"},{"key":"16_CR115","unstructured":"Zhao, M., et al.: Advances in 4D representation: geometry, motion, and interaction. arXiv preprint arXiv:2510.19255 (2025)"},{"key":"16_CR116","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: DEPR: depth guided single-view scene reconstruction with instance-level diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5722\u20135733 (2025)","DOI":"10.1109\/ICCV51701.2025.00542"},{"key":"16_CR117","doi-asserted-by":"crossref","unstructured":"Zhen, H., et al.: Tesseract: learning 4D embodied world models. arXiv preprint arXiv:2504.20995 (2025)","DOI":"10.1109\/ICCV51701.2025.00507"},{"key":"16_CR118","unstructured":"Zhong, C., et al.: TIDEGS: scalable training of over one billion 3D gaussian splatting primitives via out-of-core optimization. arXiv preprint arXiv:2605.20150 (2026)"},{"key":"16_CR119","doi-asserted-by":"crossref","unstructured":"Zhu, W., et\u00a0al.: 4D-bench: benchmarking multi-modal large language models for 4D object understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21129\u201321143 (2025)","DOI":"10.1109\/ICCV51701.2025.01963"},{"issue":"6","key":"16_CR120","first-page":"1","volume":"44","author":"X Zhu","year":"2025","unstructured":"Zhu, X., et al.: Imaginarium: vision-guided high-quality 3D scene layout generation. ACM Trans. Graph. (TOG) 44(6), 1\u201324 (2025)","journal-title":"ACM Trans. Graph. (TOG)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36839-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:32:14Z","timestamp":1789317134000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36839-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368386","9783032368393"],"references-count":120,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36839-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}