{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:23Z","timestamp":1788937583755,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_13","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:11:22Z","timestamp":1788934282000},"page":"223-241","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inference-Time Motion Calibration for\u00a0Video Generation"],"prefix":"10.1007","author":[{"given":"Zile","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ser-nam","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Almog, G., Shamir, A., Fried, O.: REED-VAE: RE-encode decode training for iterative image editing with diffusion models. Comput. Graph. Forum (Proceedings of Eurographics) (2025)","DOI":"10.1111\/cgf.70020"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Ban, Y., Wang, R., Zhou, T., Cheng, M., Gong, B., Hsieh, C.J.: Understanding the impact of negative prompts: When and how do they take effect? arXiv preprint: https:\/\/arxiv.org\/abs\/2406.02965 (2024)","DOI":"10.1007\/978-3-031-73024-5_12"},{"key":"13_CR3","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint: arXiv:2311.15127 (2023)"},{"key":"13_CR4","unstructured":"Chen, G., et\u00a0al.: SkyReels-V2: infinite-length film generative model. arXiv preprint: arXiv:2504.13074 (2025)"},{"key":"13_CR5","unstructured":"Chen, H., et al.: VideoCrafter1: open diffusion models for high-quality video generation. arXiv preprint: arXiv:2310.19512 (2023). referenced as VideoCrafter-1.0 in VBench++"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: VideoCrafter2: overcoming data limitations for high-quality video diffusion models. arXiv preprint: arXiv:2401.09047 (2024). referenced as VideoCrafter-2.0 in VBench","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"13_CR7","unstructured":"Chen, X., et al.: SEINE: short-to-long video diffusion model for generative transition and prediction. In: ICCV (2023)"},{"key":"13_CR8","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 8780\u20138794 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/49ad23d1ec9fa4bd8d77d02681df5cfa-Abstract.html"},{"key":"13_CR9","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis (2024). https:\/\/arxiv.org\/abs\/2403.03206"},{"key":"13_CR10","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint: arXiv:2307.04725 (2023)"},{"key":"13_CR11","unstructured":"He, H., et al.: Scaling image and video generation via test-time evolutionary search (2025). https:\/\/arxiv.org\/abs\/2505.17618"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Ho, J., et al.: Video diffusion models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 28334\u201328347 (2022)","DOI":"10.52202\/068431-0628"},{"key":"13_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"13_CR14","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv:2207.12598 (2022)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: VBench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Ji, P., Xiao, C., Tai, H., Huo, M.: T2VBench: benchmarking temporal dynamics for text-to-video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2024). evGenFM Workshop","DOI":"10.1109\/CVPRW63382.2024.00541"},{"key":"13_CR17","unstructured":"Kim, S., Kim, M., Park, D.: Test-time alignment of diffusion models without reward over-optimization. In: International Conference on Learning Representations (ICLR) (2025). https:\/\/openreview.net\/forum?id=vi3DjUhFVm"},{"key":"13_CR18","unstructured":"Kong, W., et al.: HunyuanVideo: a systematic framework for large video generative models (2024)"},{"key":"13_CR19","unstructured":"Kong, W., et al.: HunyuanVideo: a systematic framework for large video generative models (2025). https:\/\/arxiv.org\/abs\/2412.03603"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Koulischer, F., Handke, F., Deleu, J., Demeester, T., Ambrogioni, L.: Feedback guidance of diffusion models. arXiv preprint: https:\/\/arxiv.org\/abs\/2506.06085 (2025)","DOI":"10.52202\/085713-2690"},{"key":"13_CR21","unstructured":"Kuaishou: Kling: AI video generation model (2024). https:\/\/klingai.kuaishou.com\/. Accessed 06 June 2024"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wang, Y., Liu, Y., Zhang, Z., Wang, T.: FlowVid: taming imperfect optical flows for consistent video-to-video synthesis. arXiv preprint: arXiv:2312.08537 (2024)","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024). https:\/\/openaccess.thecvf.com\/content\/WACV2024\/papers\/Lin_Common_Diffusion_Noise_Schedules_and_Sample_Steps_Are_Flawed_WACV_2024_paper.pdf","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"13_CR24","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint: arXiv:2210.02747 (2022)"},{"key":"13_CR25","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint: arXiv:2209.03003 (2022)"},{"key":"13_CR26","unstructured":"Liu, Y., et al.: Redefining temporal modeling in video diffusion: the vectorized timestep approach. arXiv preprint: arXiv:2410.03160 (2024)"},{"key":"13_CR27","unstructured":"Ma, N., et al.: Inference-time scaling for diffusion models beyond scaling denoising steps. arXiv preprint: https:\/\/arxiv.org\/abs\/2501.09732 (2025)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Ma, N., et al.: Scaling inference time compute for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/papers\/Ma_Scaling_Inference_Time_Compute_for_Diffusion_Models_CVPR_2025_paper.pdf","DOI":"10.1109\/CVPR52734.2025.00241"},{"key":"13_CR29","unstructured":"Ma, X., et al.: Latte: latent diffusion transformer for video generation. arXiv preprint: arXiv:2401.03048 (2024)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, J., Lee, D., Ye, J.C.: Optical-flow guided prompt optimization for coherent video generation. arXiv preprint (2025)","DOI":"10.1109\/CVPR52734.2025.00734"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Ni, S., Li, C., Liu, Z.: Conditional image-to-video generation with latent flow diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18451\u201318461 (2023)","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"13_CR32","unstructured":"OpenAI: Sora: Creating video from text (2024). https:\/\/openai.com\/index\/sora\/. Accessed 15 Feb 2024"},{"key":"13_CR33","unstructured":"Pandey, K., Sofian, F.M., Draxler, F., Karaletsos, T., Mandt, S.: Variational control for guidance in diffusion models. arXiv preprint: https:\/\/arxiv.org\/abs\/2502.03686 (2025)"},{"key":"13_CR34","unstructured":"Park, Y., Jung, H., Bae, S., Yun, S.Y.: Temporal alignment guidance: on-manifold sampling in diffusion models. arXiv preprint: arXiv:2510.11057 (2025)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Ramesh, V., Mardani, M.: Test-time scaling of diffusion models via noise trajectory search (2025). https:\/\/arxiv.org\/abs\/2506.03164","DOI":"10.52202\/085713-2919"},{"key":"13_CR36","unstructured":"Ren, W., et al.: Consisti2V: enhancing visual consistency for image-to-video generation (2024). https:\/\/arxiv.org\/abs\/2402.04324"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR38","unstructured":"Runway: Gen-2: Next-generation video generation (2023). https:\/\/research.runwayml.com\/gen2. Accessed 25 Sep 2023"},{"key":"13_CR39","unstructured":"Runway: Gen-3: Scaling video generation models (2024). https:\/\/runwayml.com\/research\/introducing-gen-3-alpha. Accessed 17 June 2024"},{"key":"13_CR40","unstructured":"Sadat, S., Hilliges, O., Weber, R.M.: Eliminating oversaturation and artifacts of high guidance scales in diffusion models. In: International Conference on Learning Representations (ICLR) (2025). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/hash\/d1450d6c10c6b6cf1b80964357f5fa08-Abstract-Conference.html"},{"key":"13_CR41","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint: arXiv:2010.02502 (2020)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Sun, X., Zhang, Z., Qiao, Y., Wang, G., Wang, H.: TwoStreamVAN: improving motion modeling in video generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2743\u20132751 (2020)","DOI":"10.1109\/WACV45572.2020.9093557"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"13_CR44","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models (2025). https:\/\/arxiv.org\/abs\/2503.20314"},{"key":"13_CR45","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint: arXiv:2503.20314 (2025)"},{"key":"13_CR46","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: ModelScope text-to-video technical report. arXiv preprint: arXiv:2308.06071 (2023)"},{"key":"13_CR47","unstructured":"Wang, Y., et\u00a0al.: Dynamic negative guidance of diffusion models. arXiv preprint: https:\/\/arxiv.org\/abs\/2410.14398 (2024)"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Wu, S.C.: LatentPS: image editing using latent representations in diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pp. 130\u2013139 (2025)","DOI":"10.1109\/WACVW65960.2025.00023"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Wu, W., Chen, A., Zhang, L., Wang, L., Wang, Z., Liu, H.: Mind the time: temporally-controlled multi-event video generation. arXiv preprint (2025)","DOI":"10.1109\/CVPR52734.2025.02234"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: DynamiCrafter: animating open-domain images with video diffusion priors. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"13_CR51","unstructured":"Xu, J., et al.: EasyAnimate: a high-performance long video generation method based on transformer architecture. arXiv preprint: arXiv:2405.18991 (2024)"},{"key":"13_CR52","unstructured":"Yang, Z., et al.: CogVideoX: text-to-video diffusion models with an expert transformer (2025). https:\/\/arxiv.org\/abs\/2408.06072"},{"key":"13_CR53","unstructured":"Yang, Z., et\u00a0al.: CogVideoX: text-to-video diffusion models with an expert transformer. arXiv preprint: arXiv:2408.06072 (2024)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Yehezkel, S., Dahary, O., Voynov, A., Cohen-Or, D.: Navigating with annealing guidance scale in diffusion space. arXiv preprint: https:\/\/arxiv.org\/abs\/2506.24108 (2025)","DOI":"10.1145\/3757377.3763830"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Yuan, S., et al.: Identity-preserving text-to-video generation by frequency decomposition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12978\u201312988 (2025)","DOI":"10.1109\/CVPR52734.2025.01211"},{"key":"13_CR56","unstructured":"Zhang, L., Agrawala, M.: Packing input frame context in next-frame prediction models for video generation. arXiv preprint: arXiv:2504.12626 (2025)"},{"key":"13_CR57","unstructured":"Zhang, S., et al.: I2VGen-XL: high-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint: arXiv:2311.04145 (2023)"},{"key":"13_CR58","unstructured":"Zhang, X., et al.: Inference-time scaling of diffusion models through classical search. arXiv preprint: https:\/\/arxiv.org\/abs\/2505.23614 (2025)"},{"key":"13_CR59","unstructured":"Zhao, Z., et al.: Motion prompting: controlling video generation with motion trajectories. arXiv preprint: arXiv:2404.03073 (2024)"},{"key":"13_CR60","unstructured":"Zheng, D., et al.: VBench-2.0: advancing video generation benchmark suite for intrinsic faithfulness. arXiv preprint: arXiv:2503.21755 (2025)"}],"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\/978-3-032-37359-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:11:38Z","timestamp":1788934298000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_13","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":"10 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"}}]}}