{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:02:17Z","timestamp":1789722137951,"version":"4.0.1"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374219","type":"print"},{"value":"9783032374226","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\/978-3-032-37422-6_16","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:09:26Z","timestamp":1789718966000},"page":"276-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SIFT: Self-Imagination Fine-Tuning for\u00a0Physically Plausible Motion in\u00a0Video Diffusion Models"],"prefix":"10.1007","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiepeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"16_CR1","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv (2025)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"16_CR3","unstructured":"Bansal, H., et al.: Videophy: evaluating physical commonsense for video generation. arXiv (2024)"},{"key":"16_CR4","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv (2023)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Burgert, R., et al.: Go-with-the-flow: motion-controllable video diffusion models using real-time warped noise. In: CVPR, pp. 13\u201323 (2025)","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"16_CR6","unstructured":"Chefer, H., et al.: Videojam: joint appearance-motion representations for enhanced motion generation in video models. arXiv (2025)"},{"key":"16_CR7","unstructured":"Chen, H., et\u00a0al.: Videocrafter1: open diffusion models for high-quality video generation. arXiv (2023)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter2: overcoming data limitations for high-quality video diffusion models. In: CVPR, pp. 7310\u20137320 (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"16_CR9","unstructured":"Chen, T.S., et al.: Panda-70m: captioning 70m videos with multiple cross-modality teachers"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Chu, R., et al.: Wan-move: motion-controllable video generation via latent trajectory guidance. arXiv:2512.08765 arXiv preprint (2025)","DOI":"10.52202\/085713-0014"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"16_CR12","unstructured":"Fu, X., et al.: 3dtrajmaster: mastering 3d trajectory for multi-entity motion in video generation. arXiv (2024)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Geng, Z., Deng, M., Bai, X., Kolter, J.Z., He, K.: Mean flows for one-step generative modeling. arXiv (2025)","DOI":"10.52202\/085713-2534"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Gillman, N., et al.: Force prompting: video generation models can learn and generalize physics-based control signals. arXiv (2025)","DOI":"10.52202\/085713-3448"},{"key":"16_CR15","unstructured":"Google DeepMind: Gemini image \u2014 nano banana (2025). https:\/\/deepmind.google\/models\/gemini-image\/. Accessed 03 Mar 2026"},{"key":"16_CR16","unstructured":"Google DeepMind: Veo 3 (2025). https:\/\/deepmind.google\/models\/veo\/"},{"key":"16_CR17","unstructured":"Guo, Y., et al.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. arXiv (2023)"},{"key":"16_CR18","unstructured":"He, H., et al.: Cameractrl: enabling camera control for text-to-video generation. arXiv:2404.02101 arXiv preprint (2024)"},{"key":"16_CR19","unstructured":"Ho, J., et al.: Imagen video: high definition video generation with diffusion models. arXiv (2022)"},{"key":"16_CR20","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS (2020)"},{"key":"16_CR21","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv (2022)"},{"key":"16_CR22","unstructured":"Hou, C., Chen, Z.: Training-free camera control for video generation. arXiv (2024)"},{"key":"16_CR23","unstructured":"Hurst, A., et al.: Gpt-4o system card. arXiv (2024)"},{"key":"16_CR24","first-page":"48955","volume":"37","author":"X Ju","year":"2024","unstructured":"Ju, X., et al.: Miradata: a large-scale video dataset with long durations and structured captions. NeurIPS 37, 48955\u201348970 (2024)","journal-title":"NeurIPS"},{"key":"16_CR25","unstructured":"Kang, B., et al.: How far is video generation from world model: a physical law perspective. arXiv (2024)"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. In: ICCV, pp. 15954\u201315964 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"16_CR27","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv (2024)"},{"key":"16_CR28","unstructured":"Kuaishou: Kling AI (2025). https:\/\/app.klingai.com\/global\/"},{"key":"16_CR29","unstructured":"Lian, L., Shi, B., Yala, A., Darrell, T., Li, B.: LLM-grounded video diffusion models. arXiv (2023)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Z., et\u00a0al.: Towards understanding camera motions in any video. arXiv (2025)","DOI":"10.52202\/085713-4477"},{"key":"16_CR31","unstructured":"Ling, P., et al.: Motionclone: training-free motion cloning for controllable video generation. arXiv (2024)"},{"key":"16_CR32","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv (2022)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Liu, S., Ren, Z., Gupta, S., Wang, S.: Physgen: rigid-body physics-grounded image-to-video generation. In: ECCV, pp. 360\u2013378. Springer (2024)","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"16_CR34","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv (2022)"},{"key":"16_CR35","unstructured":"Liu, Y., et\u00a0al.: Sora: a review on background, technology, limitations, and opportunities of large vision models. arXiv (2024)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Lv, J., et al.: Gpt4motion: scripting physical motions in text-to-video generation via blender-oriented GPT planning. In: CVPR, pp. 1430\u20131440 (2024)","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"16_CR37","unstructured":"Ma, G., et\u00a0al.: Step-video-t2v technical report: the practice, challenges, and future of video foundation model. arXiv (2025)"},{"key":"16_CR38","unstructured":"Ma, X., et al.: Latte: latent diffusion transformer for video generation. arXiv (2024)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, X., Aizawa, K.: Guided image synthesis via initial image editing in diffusion model. In: ACM Multimedia, pp. 5321\u20135329 (2023)","DOI":"10.1145\/3581783.3612191"},{"key":"16_CR40","unstructured":"Meng, F., et al.: Towards world simulator: crafting physical commonsense-based benchmark for video generation. arXiv (2024)"},{"key":"16_CR41","unstructured":"Nan, K., et al.: Openvid-1m: a large-scale high-quality dataset for text-to-video generation. arXiv (2024)"},{"key":"16_CR42","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv (2021)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"16_CR44","unstructured":"Pexels: Pexels \u2013 free stock photos, royalty free images & videos (2025). https:\/\/www.pexels.com\/. Accessed 13 Nov 2025"},{"key":"16_CR45","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv (2022)"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)","DOI":"10.52202\/068431-2643"},{"key":"16_CR48","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"16_CR49","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv (2020)"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Sun, K., et al.: T2v-compbench: a comprehensive benchmark for compositional text-to-video generation. In: CVPR, pp. 8406\u20138416 (2025)","DOI":"10.1109\/CVPR52734.2025.00787"},{"key":"16_CR51","unstructured":"Tan, X., et al.: Physmotion: physics-grounded dynamics from a single image. arXiv (2024)"},{"key":"16_CR52","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv (2024)"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"16_CR54","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv (2025)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Physctrl: generative physics for controllable and physics-grounded video generation. arXiv (2025)","DOI":"10.52202\/085713-5598"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Wang, Q., et\u00a0al.: Koala-36m: a large-scale video dataset improving consistency between fine-grained conditions and video content. In: CVPR, pp. 8428\u20138437 (2025)","DOI":"10.1109\/CVPR52734.2025.00789"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Wang, R., Huang, H., Zhu, Y., Russakovsky, O., Wu, Y.: The silent assistant: noisequery as implicit guidance for goal-driven image generation. In: ICCV, pp. 17618\u201317628 (2025)","DOI":"10.1109\/ICCV51701.2025.01637"},{"key":"16_CR58","unstructured":"Wang, Y., et\u00a0al.: Internvid: a large-scale video-text dataset for multimodal understanding and generation. arXiv (2023)"},{"key":"16_CR59","unstructured":"Wang, Y., et\u00a0al.: Internvideo2. 5: empowering video MLLMs with long and rich context modeling. arXiv (2025)"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Customcrafter: customized video generation with preserving motion and concept composition abilities. In: AAAI. vol. 39, pp. 8469\u20138477 (2025)","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"16_CR61","doi-asserted-by":"crossref","unstructured":"Wu, T., Si, C., Jiang, Y., Huang, Z., Liu, Z.: Freeinit: bridging initialization gap in video diffusion models. In: ECCV, pp. 378\u2013394. Springer (2024)","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Xie, T., Zhao, Y., Jiang, Y., Jiang, C.: Physanimator: physics-guided generative cartoon animation. In: CVPR, pp. 10793\u201310804 (2025)","DOI":"10.1109\/CVPR52734.2025.01008"},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Xue, Q., Yin, X., Yang, B., Gao, W.: Phyt2v: LLM-guided iterative self-refinement for physics-grounded text-to-video generation. In: CVPR, pp. 18826\u201318836 (2025)","DOI":"10.1109\/CVPR52734.2025.01754"},{"key":"16_CR64","unstructured":"Xue, Z., et\u00a0al.: Ultravideo: high-quality UHD video dataset with comprehensive captions. arXiv (2025)"},{"key":"16_CR65","unstructured":"Yang, X., et\u00a0al.: Towards physically plausible video generation via VLM planning. arXiv 2 (2025)"},{"key":"16_CR66","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv (2024)"},{"key":"16_CR67","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. arXiv (2024)"},{"key":"16_CR68","unstructured":"Zhang, K., Xiao, C., Mei, Y., Xu, J., Patel, V.M.: Think before you diffuse: LLMs-guided physics-aware video generation. arXiv (2025)"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Physdreamer: physics-based interaction with 3d objects via video generation. In: ECCV, pp. 388\u2013406. Springer (2024)","DOI":"10.1007\/978-3-031-72627-9_22"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Videorepa: learning physics for video generation through relational alignment with foundation models. arXiv (2025)","DOI":"10.52202\/085713-4091"},{"key":"16_CR71","unstructured":"Zheng, Z., et al.: Open-sora: democratizing efficient video production for all. arXiv (2024)"}],"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\/978-3-032-37422-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:10:04Z","timestamp":1789719004000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37422-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374219","9783032374226"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37422-6_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":"19 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"}}]}}