{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:58:44Z","timestamp":1790279924215,"version":"4.1.0"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","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\/978-3-032-36984-0_9","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:00:07Z","timestamp":1790276407000},"page":"155-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PhysChoreo: Physics-Controllable Video Generation with\u00a0Part-Aware Semantic Grounding"],"prefix":"10.1007","author":[{"given":"Haoze","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"9_CR1","unstructured":"Bansal, H., et al.: Videophy: evaluating physical commonsense for video generation (2024). arXiv preprint arXiv:2406.03520"},{"key":"9_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). arXiv preprint arXiv:2311.15127"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Physgen3d: crafting a miniature interactive world from a single image. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6178\u20136189 (2025)","DOI":"10.1109\/CVPR52734.2025.00579"},{"key":"9_CR4","unstructured":"Chen, H., et\u00a0al.: Videocrafter1: open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter2: overcoming data limitations for high-quality video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7310\u20137320 (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"9_CR6","unstructured":"DeepMind, G.: Veo: a text-to-video generation system. Tech. Rep. Tech. Report, Google LLC (2025). https:\/\/storage.googleapis.com\/deepmind-media\/veo\/Veo-3-Tech-Report.pdf, version 3"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Gillman, N., et al.: Force prompting: video generation models can learn and generalize physics-based control signals. Adv. Neural Inf. Process. Syst. 38, 103174\u2013103201 (2026)","DOI":"10.52202\/085713-3448"},{"key":"9_CR8","unstructured":"Glm, T., et\u00a0al.: Chatglm: a family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793 (2024)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Z., et\u00a0al.: Diffusion as shader: 3d-aware video diffusion for versatile video generation control. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201312 (2025)","DOI":"10.1145\/3721238.3730607"},{"key":"9_CR10","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation (2022). arXiv preprint arXiv:2211.13221"},{"key":"9_CR11","unstructured":"Hu, Y., et al.: Difftaichi: differentiable programming for physical simulation (2019). arXiv preprint arXiv:1910.00935"},{"issue":"6","key":"9_CR12","first-page":"1","volume":"38","author":"Y Hu","year":"2019","unstructured":"Hu, Y., Li, T.M., Anderson, L., Ragan-Kelley, J., Durand, F.: Taichi: a language for high-performance computation on spatially sparse data structures. ACM Trans. Graph. (TOG) 38(6), 1\u201316 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"9_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459671","volume":"40","author":"Y Hu","year":"2021","unstructured":"Hu, Y., et al.: Quantaichi: a compiler for quantized simulations. ACM Trans. Graph. (TOG) 40(4), 1\u201316 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Huang, T., et al.: Dreamphysics: learning physics-based 3d dynamics with video diffusion priors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 3733\u20133741 (2025)","DOI":"10.1609\/aaai.v39i4.32389"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, C., Schroeder, C., Teran, J., Stomakhin, A., Selle, A.: The material point method for simulating continuum materials. In: ACM SIGGRAPH 2016 Courses, pp. 1\u201352 (2016)","DOI":"10.1145\/2897826.2927348"},{"key":"9_CR16","unstructured":"Kang, B., et al.: How far is video generation from world model: a physical law perspective (2024). arXiv preprint arXiv:2411.02385"},{"key":"9_CR17","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"9_CR18","unstructured":"Le, L., et al.: Pixie: fast and generalizable supervised learning of 3d physics from pixels (2025). arXiv preprint arXiv:2508.17437"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., Xing, Z., Wang, R., Zhang, H., Dai, Q., Wu, Z.: Magicmotion: controllable video generation with dense-to-sparse trajectory guidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12112\u201312123 (2025)","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Wonderplay: dynamic 3D scene generation from a single image and actions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.00849"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Liang, J., Fan, Y., Zhang, K., Timofte, R., Van Gool, L., Ranjan, R.: MoVideo: motion-aware video generation with diffusion model. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15102, pp. 56\u201374. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72784-9_4","DOI":"10.1007\/978-3-031-72784-9_4"},{"key":"9_CR22","unstructured":"Lin, Y., Lin, C., Xu, J., Mu, Y.: Omniphysgs: 3d constitutive gaussians for general physics-based dynamics generation. arXiv preprint arXiv:2501.18982 (2025)"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Partfield: learning 3d feature fields for part segmentation and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9704\u20139715 (2025)","DOI":"10.1109\/ICCV51701.2025.00905"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Partslip: low-shot part segmentation for 3d point clouds via pretrained image-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21736\u201321746 (2023)","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Liu, S., Ren, Z., Gupta, S., Wang, S.: PhysGen: rigid-body physics-grounded image-to-video generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15140, pp. 360\u2013378. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73007-8_21","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15105, pp. 38\u201355. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ye, W., Luximon, Y., Wan, P., Zhang, D.: Unleashing the potential of multi-modal foundation models and video diffusion for 4D dynamic physical scene simulation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11016\u201311025 (2025)","DOI":"10.1109\/CVPR52734.2025.01029"},{"key":"9_CR28","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts (2016). arXiv preprint arXiv:1608.03983"},{"key":"9_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv preprint arXiv:1711.05101"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Mittal, H., Zhuang, P., Lee, H.Y., Tulsiani, S.: Uniphy: learning a unified constitutive model for inverse physics simulation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16208\u201316218 (2025)","DOI":"10.1109\/CVPR52734.2025.01511"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Mo, K., et al.: Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"M\u00fcller, M., Macklin, M., Chentanez, N., Jeschke, S., Kim, T.Y.: Detailed rigid body simulation with extended position based dynamics. Comput. Graph. Forum 39, 101\u2013112. Wiley Online Library (2020)","DOI":"10.1111\/cgf.14105"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Ni, H., Shi, C., Li, K., Huang, S.X., Min, M.R.: Conditional image-to-video generation with latent flow diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18444\u201318455 (2023)","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"9_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2025.103431","volume":"156","author":"M Png","year":"2025","unstructured":"Png, M., Huang, M., Bahreman, M., Kube, C.M., Lowe, M.J., Lan, B.: Accurate wave velocity measurement from diffuse wave fields. NDT & E International 156, 103431 (2025)","journal-title":"NDT & E International"},{"key":"9_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR36","unstructured":"Ren, T., et\u00a0al.: Grounded sam: assembling open-world models for diverse visual tasks. arxiv 2024. arXiv preprint arXiv:2401.14159"},{"key":"9_CR37","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Shuai, Y., et\u00a0al.: Pugs: zero-shot physical understanding with gaussian splatting. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 4478\u20134485. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128683"},{"key":"9_CR39","unstructured":"Singh, A., et\u00a0al.: Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"9_CR40","unstructured":"Su, H., Huang, T., Wan, Z., Wu, X., Zuo, W.: S$$^2$$am3d: scale-controllable part segmentation of 3d point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14357\u201314366 (2026)"},{"key":"9_CR41","unstructured":"Tan, X., et al.: Physmotion: physics-grounded dynamics from a single image. arxiv preprint arXiv:2411.17189 (2024)"},{"key":"9_CR42","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models (2023). arXiv preprint arXiv:2312.11805"},{"key":"9_CR43","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Physctrl: generative physics for controllable and physics-grounded video generation. arXiv preprint arXiv:2509.20358 (2025)","DOI":"10.52202\/085713-5598"},{"key":"9_CR45","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":"9_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Lavie: high-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vis. 133(5), 3059\u20133078 (2025)","DOI":"10.1007\/s11263-024-02295-1"},{"key":"9_CR47","unstructured":"Wiedemer, T., et al.: Video models are zero-shot learners and reasoners (2025). arXiv preprint arXiv:2509.20328"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Xie, T., Zhao, Y., Jiang, Y., Jiang, C.: Physanimator: physics-guided generative cartoon animation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10793\u201310804 (2025)","DOI":"10.1109\/CVPR52734.2025.01008"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: Physgaussian: physics-integrated 3d gaussians for generative dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4389\u20134398 (2024)","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"9_CR50","doi-asserted-by":"publisher","unstructured":"Xing, J., et al.: DynamiCrafter: animating open-domain images with video diffusion priors. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15104, pp. 399\u2013417. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72952-2_23","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"9_CR51","unstructured":"Xu, J., Cheng, W., Gao, Y., Wang, X., Gao, S., Shan, Y.: Instantmesh: efficient 3d mesh generation from a single image with sparse-view large reconstruction models. arXiv preprint arXiv:2404.07191 (2024)"},{"key":"9_CR52","unstructured":"Yang, Y., et al.: Sampart3d: segment any part in 3d objects (2024). arXiv preprint arXiv:2411.07184"},{"key":"9_CR53","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Zhai, A.J., et al.: Physical property understanding from language-embedded feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28296\u201328305 (2024)","DOI":"10.1109\/CVPR52733.2024.02673"},{"key":"9_CR55","doi-asserted-by":"publisher","unstructured":"Zhang, T., et al.: PhysDreamer: physics-based interaction with 3d objects via video generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15060. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72627-9_22","DOI":"10.1007\/978-3-031-72627-9_22"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"}],"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\/978-3-032-36984-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:00:21Z","timestamp":1790276421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_9","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":"25 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"}}]}}