{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:31:27Z","timestamp":1772040687383,"version":"3.50.1"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-3-031-72627-9_22","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"388-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["PhysDreamer: Physics-Based Interaction with\u00a03D Objects via\u00a0Video Generation"],"prefix":"10.1007","author":[{"given":"Tianyuan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Hong-Xing","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Rundi","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Brandon Y.","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Changxi","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Noah","family":"Snavely","sequence":"additional","affiliation":[]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[]},{"given":"William T.","family":"Freeman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Attal, B., et al.: Hyperreel: high-fidelity 6-dof video with ray-conditioned sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16610\u201316620 (2023)","DOI":"10.1109\/CVPR52729.2023.01594"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: 4d-fy: text-to-4d generation using hybrid score distillation sampling. arXiv preprint arXiv:2311.17984 (2023)","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"22_CR3","unstructured":"Bar-Tal, O., et\u00a0al.: Lumiere: A space-time diffusion model for video generation. arXiv preprint arXiv:2401.12945 (2024)"},{"key":"22_CR4","unstructured":"Blattmann, A., , et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"22_CR6","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Y., Wang, J., Yuille, A., Zhou, Z., Wang, A.: Structure-aware sparse-view x-ray 3d reconstruction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01062"},{"key":"22_CR8","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":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3d generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"22_CR10","unstructured":"Chen, H.y., et al.: Virtual elastic objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15827\u201315837 (2022)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Livephoto: real image animation with text-guided motion control. arXiv preprint arXiv:2312.02928 (2023)","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Chuang, Y.Y., Goldman, D.B., Zheng, K.C., Curless, B., Salesin, D.H., Szeliski, R.: Animating pictures with stochastic motion textures. In: ACM SIGGRAPH 2005 Papers, pp. 853\u2013860 (2005)","DOI":"10.1145\/1186822.1073273"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Proceedings of the 23rd Annual Conference On Computer Graphics and Interactive Techniques, pp. 303\u2013312 (1996)","DOI":"10.1145\/237170.237269"},{"key":"22_CR14","unstructured":"Dai, Z., et al..: Animateanything: fine-grained open domain image animation with motion guidance. arXiv e-prints pp. arXiv\u20132311 (2023)"},{"issue":"6","key":"22_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818095","volume":"34","author":"A Davis","year":"2015","unstructured":"Davis, A., Chen, J.G., Durand, F.: Image-space modal bases for plausible manipulation of objects in video. ACM Trans. Graph. (TOG) 34(6), 1\u20137 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR16","unstructured":"Davis, M.A.: Visual vibration analysis. Ph.D. thesis, Massachusetts Institute of Technology (2016)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Duan, Y., Wei, F., Dai, Q., He, Y., Chen, W., Chen, B.: 4d gaussian splatting: Towards efficient novel view synthesis for dynamic scenes. arXiv preprint arXiv:2402.03307 (2024)","DOI":"10.1145\/3641519.3657463"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Feng, Y., Shang, Y., Li, X., Shao, T., Jiang, C., Yang, Y.: Pie-nerf: physics-based interactive elastodynamics with nerf. arXiv preprint arXiv:2311.13099 (2023)","DOI":"10.1109\/CVPR52733.2024.00426"},{"key":"22_CR19","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":"22_CR20","first-page":"33768","volume":"35","author":"H Gao","year":"2022","unstructured":"Gao, H., Li, R., Tulsiani, S., Russell, B., Kanazawa, A.: Monocular dynamic view synthesis: A reality check. Adv. Neural. Inf. Process. Syst. 35, 33768\u201333780 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR21","unstructured":"Geng, D., Owens, A.: Motion guidance: diffusion-based image editing with differentiable motion estimators. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Emu video: Factorizing text-to-video generation by explicit image conditioning. arXiv preprint arXiv:2311.10709 (2023)","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Guo, X., et al.: Forward flow for novel view synthesis of dynamic scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16022\u201316033 (2023)","DOI":"10.1109\/ICCV51070.2023.01468"},{"key":"22_CR24","unstructured":"Gupta, A., et al.: Photorealistic video generation with diffusion models. arXiv preprint arXiv:2312.06662 (2023)"},{"key":"22_CR25","unstructured":"Ho, J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"22_CR26","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"issue":"4","key":"22_CR27","first-page":"1","volume":"37","author":"Y Hu","year":"2018","unstructured":"Hu, Y., et al.: A moving least squares material point method with displacement discontinuity and two-way rigid body coupling. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"22_CR28","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)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Huang, Y.H., Sun, Y.T., Yang, Z., Lyu, X., Cao, Y.P., Qi, X.: Sc-gs: sparse-controlled gaussian splatting for editable dynamic scenes. arXiv preprint arXiv:2312.14937 (2023)","DOI":"10.1109\/CVPR52733.2024.00404"},{"issue":"4","key":"22_CR30","first-page":"1","volume":"36","author":"C Jiang","year":"2017","unstructured":"Jiang, C., Gast, T., Teran, J.: Anisotropic elastoplasticity for cloth, knit and hair frictional contact. ACM Trans. Graph. (TOG) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"22_CR31","first-page":"1","volume":"34","author":"C Jiang","year":"2015","unstructured":"Jiang, C., Schroeder, C., Selle, A., Teran, J., Stomakhin, A.: The affine particle-in-cell method. ACM Trans. Graph. (TOG) 34(4), 1\u201310 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR32","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":"22_CR33","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. 42(4) (2023)","DOI":"10.1145\/3592433"},{"issue":"4","key":"22_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925906","volume":"35","author":"G Kl\u00e1r","year":"2016","unstructured":"Kl\u00e1r, G., et al.: Drucker-prager elastoplasticity for sand animation. ACM Trans. Graph. (TOG) 35(4), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Kobayashi, M., Motoyoshi, I.: Perceiving natural speed in natural movies. i-Perception 10(4), 2041669519860544 (2019)","DOI":"10.1177\/2041669519860544"},{"key":"22_CR36","unstructured":"Kondratyuk, D., et\u00a0al.: Videopoet: a large language model for zero-shot video generation. arXiv preprint arXiv:2312.14125 (2023)"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Kopf, J., Rong, X., Huang, J.B.: Robust consistent video depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1611\u20131621 (2021)","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Kratimenos, A., Lei, J., Daniilidis, K.: Dynmf: neural motion factorization for real-time dynamic view synthesis with 3D gaussian splatting. arXiv preprint arXiv:2312.00112 (2023)","DOI":"10.1007\/978-3-031-72986-7_15"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Le\u00a0Cleac\u2019h, S., et al.: Differentiable physics simulation of dynamics-augmented neural objects. IEEE Robotics and Automation Letters (2023)","DOI":"10.1109\/LRA.2023.3257707"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. In: Computer graphics forum, vol.\u00a027, pp. 1421\u20131430. Wiley Online Library (2008)","DOI":"10.1111\/j.1467-8659.2008.01282.x"},{"key":"22_CR41","unstructured":"Li, X., et al.: Pac-nerf: physics augmented continuum neural radiance fields for geometry-agnostic system identification. arXiv preprint arXiv:2303.05512 (2023)"},{"key":"22_CR42","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":"22_CR43","doi-asserted-by":"crossref","unstructured":"Li, Z., Tucker, R., Snavely, N., Holynski, A.: Generative image dynamics. arXiv preprint arXiv:2309.07906 (2023)","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Q., Cole, F., Tucker, R., Snavely, N.: Dynibar: neural dynamic image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4273\u20134284 (2023)","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"22_CR45","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. arXiv preprint arXiv:2312.13763 (2023)","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"22_CR46","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"},{"key":"22_CR47","unstructured":"Ma, P., et al.: Learning neural constitutive laws from motion observations for generalizable pde dynamics. In: International Conference on Machine Learning. PMLR (2023)"},{"key":"22_CR48","unstructured":"Macklin, M.: Warp: a high-performance python framework for gpu simulation and graphics. https:\/\/github.com\/nvidia\/warp (March 2022), nVIDIA GPU Technology Conference (GTC)"},{"key":"22_CR49","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":"22_CR50","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Fox, D., Seitz, S.M.: Dynamicfusion: reconstruction and tracking of non-rigid scenes in real-time. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 343\u2013352 (2015)","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"22_CR51","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"},{"key":"22_CR52","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Hypernerf: a higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228 (2021)","DOI":"10.1145\/3478513.3480487"},{"key":"22_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"key":"22_CR54","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"22_CR55","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":"22_CR56","doi-asserted-by":"crossref","unstructured":"Ram, D., et al.: A material point method for viscoelastic fluids, foams and sponges. In: Proceedings of the 14th ACM SIGGRAPH\/Eurographics Symposium on Computer Animation, pp. 157\u2013163 (2015)","DOI":"10.1145\/2786784.2786798"},{"key":"22_CR57","unstructured":"Ren, J., et al.: Dreamgaussian4d: Generative 4d gaussian splatting. arXiv preprint arXiv:2312.17142 (2023)"},{"key":"22_CR58","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. arXiv preprint arXiv:2209.14792 (2022)"},{"key":"22_CR59","unstructured":"Singer, U., et\u00a0al.: Text-to-4d dynamic scene generation. arXiv preprint arXiv:2301.11280 (2023)"},{"issue":"4","key":"22_CR60","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1038\/nn1669","volume":"9","author":"AA Stocker","year":"2006","unstructured":"Stocker, A.A., Simoncelli, E.P.: Noise characteristics and prior expectations in human visual speed perception. Nat. Neurosci. 9(4), 578\u2013585 (2006)","journal-title":"Nat. Neurosci."},{"issue":"4","key":"22_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2461912.2461948","volume":"32","author":"A Stomakhin","year":"2013","unstructured":"Stomakhin, A., Schroeder, C., Chai, L., Teran, J., Selle, A.: A material point method for snow simulation. ACM Trans. Graph. (TOG) 32(4), 1\u201310 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR62","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":"22_CR63","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric and challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"22_CR64","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: International Conference on Learning Representations (2022)"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Wang, C., MacDonald, L.E., Jeni, L.A., Lucey, S.: Flow supervision for deformable nerf. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21128\u201321137 (2023)","DOI":"10.1109\/CVPR52729.2023.02024"},{"key":"22_CR66","unstructured":"Wang, C., et al.: Diffusion priors for dynamic view synthesis from monocular videos. arXiv preprint arXiv:2401.05583 (2024)"},{"key":"22_CR67","doi-asserted-by":"publisher","unstructured":"Wu, C., et al.: N\u00fcwa: Visual synthesis pre-training for neural visual world creation. In: European Conference on Computer Vision, pp. 720\u2013736. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_41","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"22_CR68","doi-asserted-by":"crossref","unstructured":"Xian, W., Huang, J.B., Kopf, J., Kim, C.: Space-time neural irradiance fields for free-viewpoint video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9421\u20139431 (2021)","DOI":"10.1109\/CVPR46437.2021.00930"},{"key":"22_CR69","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: Physgaussian: physics-integrated 3D Gaussians for generative dynamics. arXiv preprint arXiv:2311.12198 (2023)","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Neural fields in visual computing and beyond. In: Computer Graphics Forum, vol.\u00a041, pp. 641\u2013676. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14505"},{"key":"22_CR71","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Deformable 3D Gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101 (2023)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"22_CR72","unstructured":"Yin, Y., Xu, D., Wang, Z., Zhao, Y., Wei, Y.: 4dgen: grounded 4D content generation with spatial-temporal consistency. arXiv preprint arXiv:2312.17225 (2023)"},{"key":"22_CR73","doi-asserted-by":"crossref","unstructured":"Yu, H., Julin, J., Milacski, Z.\u00c1., Niinuma, K., Jeni, L.A.: Cogs: Controllable gaussian splatting. arXiv preprint arXiv:2312.05664 (2023)","DOI":"10.1109\/CVPR52733.2024.02043"},{"key":"22_CR74","doi-asserted-by":"crossref","unstructured":"Yu, H., Julin, J., Milacski, Z.A., Niinuma, K., Jeni, L.A.: Dylin: making light field networks dynamic. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12397\u201312406 (2023)","DOI":"10.1109\/CVPR52729.2023.01193"},{"key":"22_CR75","unstructured":"Zhang, S., et al.: I2vgen-xl: high-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:2311.04145 (2023)"},{"issue":"4","key":"22_CR76","first-page":"1","volume":"40","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Cole, F., Tucker, R., Freeman, W.T., Dekel, T.: Consistent depth of moving objects in video. ACM Trans. Graph. (TOG) 40(4), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"}],"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\/978-3-031-72627-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:46:06Z","timestamp":1732920366000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 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"}}]}}