{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:08:03Z","timestamp":1790233683202,"version":"4.1.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370099","type":"print"},{"value":"9783032370105","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\/978-3-032-37010-5_4","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:51:53Z","timestamp":1790232713000},"page":"57-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Scene-Adaptive Trajectory-Controllable Human Image Animation with\u00a0Camera Movement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0371-9921","authenticated-orcid":false,"given":"Deyin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1929-5482","authenticated-orcid":false,"given":"Jicheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-058X","authenticated-orcid":false,"given":"Lin Yuanbo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1182-4502","authenticated-orcid":false,"given":"Xiaowei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9284-2955","authenticated-orcid":false,"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4501-7992","authenticated-orcid":false,"given":"Zhe","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-2245","authenticated-orcid":false,"given":"Anjan","family":"Dutta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"American society for photogrammetry and remote sensing (ASPRS): Asprs positional accuracy standards for digital geospatial data. Technical Report, ASPRS (2014). https:\/\/www.asprs.org\/wp-content\/uploads\/2015\/01\/ASPRS_Positional_Accuracy_Standards_Edition1_Version100_November2014.pdf, practical guidance for LiDAR\/DEM ground-point handling and accuracy reporting","DOI":"10.14358\/PERS.81.3.A1-A26"},{"key":"4_CR2","unstructured":"Bochkovskii, A., et al.: Depth pro: sharp monocular metric depth in less than a second (2024). https:\/\/arxiv.org\/abs\/2410.02073"},{"key":"4_CR3","unstructured":"Cao, C., Ren, X., Fu, Y.: Mvsformer++: revealing the devil in transformer\u2019s details for multi-view stereo. arXiv preprint arXiv:2401.11673, https:\/\/arxiv.org\/abs\/2401.11673 (2024)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Cao, C., e al.: Uni3c: unifying precisely 3d-enhanced camera and human motion controls for video generation. arXiv preprint arXiv:2504.14899 (2025)","DOI":"10.1145\/3757377.3763842"},{"key":"4_CR5","unstructured":"Chung, H.W., et al.: Unimax: fairer and more effective language sampling for large-scale multilingual pretraining (2023). https:\/\/arxiv.org\/abs\/2304.09151"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models (2023). https:\/\/arxiv.org\/abs\/2302.03011","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3d human motions from text. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161 (2022). https:\/\/openaccess.thecvf.com\/content\/CVPR2022\/papers\/Guo_Generating_Diverse_and_Natural_3D_Human_Motions_From_Text_CVPR_2022_paper.pdf","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"4_CR8","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium (2018). https:\/\/arxiv.org\/abs\/1706.08500"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models (2022). https:\/\/arxiv.org\/abs\/2204.03458","DOI":"10.52202\/068431-0628"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1007\/s11633-025-1545-5","volume":"22","author":"J Hu","year":"2025","unstructured":"Hu, J., Liu, K., Peng, Y., Zeng, M., Kang, W.: Exploring salient embeddings for gait recognition. Mach. Intell. Res. 22, 888\u2013899 (2025)","journal-title":"Mach. Intell. Res."},{"key":"4_CR11","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Hu, L., et al.: Animate anyone 2: high-fidelity character image animation with environment affordance (2025). https:\/\/arxiv.org\/abs\/2502.06145","DOI":"10.1109\/ICCV51701.2025.00951"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Vbench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"4_CR14","doi-asserted-by":"publisher","unstructured":"Huber, P.J.: Robust Statistics. Wiley, New York (1981). https:\/\/doi.org\/10.1002\/0471725250, foundational text on robust estimation theory","DOI":"10.1002\/0471725250"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, R., Xing, D., Sun, H., Ha, Y., Shen, J., Ho, C.: Tokenmotion: decoupled motion control via token disentanglement for human-centric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/papers\/Li_TokenMotion_Decoupled_Motion_Control_via_Token_Disentanglement_for_Human-centric_Video_CVPR_2025_paper.pdf","DOI":"10.1109\/CVPR52734.2025.00188"},{"key":"4_CR16","unstructured":"Liang, J., et al.: Realismotion: decomposed human motion control and video generation in the world space. arXiv preprint arXiv:2508.08588 (2025)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Lin, G., Jiang, J., Yang, J., Zheng, Z., Liang, C.: Omnihuman-1: rethinking the scaling-up of one-stage conditioned human animation models (2025). https:\/\/arxiv.org\/abs\/2502.01061","DOI":"10.1109\/ICCV51701.2025.01285"},{"key":"4_CR18","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow (2022). https:\/\/arxiv.org\/abs\/2209.03003"},{"issue":"6","key":"4_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015). https:\/\/doi.org\/10.1145\/2816795.2818013","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: pose-guided text-to-video generation using pose-free videos (2024). https:\/\/arxiv.org\/abs\/2304.01186","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"4_CR21","unstructured":"Niu, M., et al.: Anicrafter: customizing realistic human-centric animation via avatar-background conditioning in video diffusion models. arXiv preprint arXiv:2505.20255 (2025)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10975\u201310985 (2019). https:\/\/arxiv.org\/abs\/1904.05866","DOI":"10.1109\/CVPR.2019.01123"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers (2023). https:\/\/arxiv.org\/abs\/2212.09748","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"4_CR24","unstructured":"Peng, B., Wang, J., Zhang, Y., Li, W., Yang, M.C., Jia, J.: Controlnext: powerful and efficient control for image and video generation. arXiv preprint arXiv:2408.06070, https:\/\/arxiv.org\/abs\/2408.06070 (2024)"},{"key":"4_CR25","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision - ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision - ECCV 2016, pp. 501\u2013518. Springer International Publishing, Cham (2016)"},{"key":"4_CR26","doi-asserted-by":"publisher","unstructured":"Shen, Z., et al.: World-grounded human motion recovery via gravity-view coordinates. In: SIGGRAPH Asia 2024 Conference Papers. SA 2024, ACM, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3680528.3687565","DOI":"10.1145\/3680528.3687565"},{"key":"4_CR27","unstructured":"Song, C., Yang, Y., Zhao, T., Li, R., Zhang, C.: Worldforge: unlocking emergent 3d\/4d generation in video diffusion model via training-free guidance (2025). https:\/\/arxiv.org\/abs\/2509.15130"},{"key":"4_CR28","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"4_CR29","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. arXiv preprint arXiv:2104.09864 (2021), v5, Accessed 8 Nov 2023"},{"key":"4_CR30","unstructured":"Tan, S., et al.: Animate-x: universal character image animation with enhanced motion representation (2024). https:\/\/arxiv.org\/abs\/2410.10306"},{"key":"4_CR31","doi-asserted-by":"publisher","unstructured":"Team, W., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314, https:\/\/doi.org\/10.48550\/arXiv.2503.20314, https:\/\/arxiv.org\/abs\/2503.20314 (2025)","DOI":"10.48550\/arXiv.2503.20314"},{"key":"4_CR32","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model (2022). https:\/\/arxiv.org\/abs\/2209.14916"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Tian, J., Qu, X., Lu, Z., Wei, W., Liu, S., Cheng, Y.: Extrapolating and decoupling image-to-video generation models: motion modeling is easier than you think (2025). https:\/\/arxiv.org\/abs\/2503.00948","DOI":"10.1109\/CVPR52734.2025.01167"},{"key":"4_CR34","unstructured":"Tong, Z., Li, C., Chen, Z., Wu, B., Zhou, W.: Musepose: a pose-driven image-to-video framework for virtual human generation. arxiv (2024)"},{"key":"4_CR35","unstructured":"Tu, S., et al.: Motionfollower: editing video motion via lightweight score-guided diffusion (2024). https:\/\/arxiv.org\/abs\/2405.20325"},{"key":"4_CR36","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges (2019). https:\/\/arxiv.org\/abs\/1812.01717"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Veicht, A., Sarlin, P.E., Lindenberger, P., Pollefeys, M.: Geocalib: learning single-image calibration with geometric optimization. In: European Conference on Computer Vision (ECCV) (2024). https:\/\/arxiv.org\/abs\/2409.06704","DOI":"10.1007\/978-3-031-73661-2_1"},{"key":"4_CR38","unstructured":"Wang, T., et al.: Disco: disentangled control for referring human dance generation in real world. arXiv preprint arXiv:2307.00040 (2023)"},{"issue":"10","key":"4_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-024-4592-3","volume":"68","author":"X Wang","year":"2025","unstructured":"Wang, X., et al.: Unianimate: taming unified video diffusion models for consistent human image animation. Sci. China Inf. Sci. 68(10), 1\u201314 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Humanvid: demystifying training data for camera-controllable human image animation (2024). https:\/\/arxiv.org\/abs\/2407.17438","DOI":"10.52202\/079017-0635"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Motionctrl: a unified and flexible motion controller for video generation. In: Proceedings of the ACM SIGGRAPH 2024 Conference Papers (2024). https:\/\/wzhouxiff.github.io\/projects\/MotionCtrl\/","DOI":"10.1145\/3641519.3657518"},{"key":"4_CR42","doi-asserted-by":"publisher","unstructured":"Wilcox, R.R.: Modern Statistics for the Social and Behavioral Sciences: A Practical Introduction. Chapman & Hall\/CRC, Boca Raton, FL, 2nd edn. (2017). https:\/\/doi.org\/10.1201\/9781315154480, discussion of trimmed means and practical trimming proportions","DOI":"10.1201\/9781315154480"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Wu, T., Si, C., Jiang, Y., Huang, Z., Liu, Z.: Freeinit: bridging initialization gap in video diffusion models. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Magicanimate: temporally consistent human image animation using diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1481\u20131490 (2024)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"4_CR45","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 4210\u20134220 (2023). https:\/\/arxiv.org\/abs\/2307.15880, arXiv preprint arXiv:2307.15880"},{"key":"4_CR46","doi-asserted-by":"publisher","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV 2023), pp. 3813\u20133824. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00355","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4_CR47","unstructured":"Zhang, Y., et al.: Mimicmotion: high-quality human motion video generation with confidence-aware pose guidance (2025). https:\/\/arxiv.org\/abs\/2406.19680"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Tora: trajectory-oriented diffusion transformer for video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/papers\/Zhang_Tora_Trajectory-oriented_Diffusion_Transformer_for_Video_Generation_CVPR_2025_paper.pdf","DOI":"10.1109\/CVPR52734.2025.00198"},{"key":"4_CR49","doi-asserted-by":"publisher","unstructured":"Zhao, M., Zhu, H., Xiang, C., Zheng, K., Li, C., Jun, Z.: Identifying and solving conditional image leakage in image-to-video diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 30300\u201330326 (2024). https:\/\/doi.org\/10.52202\/079017-0954, https:\/\/cond-image-leak.github.io\/","DOI":"10.52202\/079017-0954"},{"key":"4_CR50","unstructured":"Zhou, J., et al.: Realisdance-dit: simple yet strong baseline towards controllable character animation in the wild. arXiv preprint arXiv:2504.14977 (2025)"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, S., et al.: Champ: controllable and consistent human image animation with 3d parametric guidance. In: European Conference on Computer Vision (2024). https:\/\/api.semanticscholar.org\/CorpusID:268667481","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"4_CR52","unstructured":"Zuo, Y., et al.: Edit-your-motion: space-time diffusion decoupling learning for video motion editing. arXiv preprint arXiv:2405.04496, https:\/\/arxiv.org\/abs\/2405.04496 (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\/978-3-032-37010-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:52:11Z","timestamp":1790232731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37010-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370099","9783032370105"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37010-5_4","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"}}]}}