{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:02:04Z","timestamp":1791910924647,"version":"4.3.4"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370372","type":"print"},{"value":"9783032370389","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\/978-3-032-37038-9_38","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:43:08Z","timestamp":1789123388000},"page":"668-687","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Controllable Egocentric Video Generation via\u00a0Occlusion-Aware Sparse 3D Hand Joints"],"prefix":"10.1007","author":[{"given":"Chenyangguang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Botao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Delitzas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangjinhua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"38_CR1","unstructured":"Ali, A., et\u00a0al.: World simulation with video foundation models for physical ai. arXiv preprint arXiv:2511.00062 (2025)"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Bagchi, A., Bao, Z., Bharadhwaj, H., Wang, Y.X., Tokmakov, P., Hebert, M.: Walk through paintings: Egocentric world models from internet priors, (2026). arXiv preprint arXiv:2601.15284","DOI":"10.1007\/978-3-032-37098-3_26"},{"key":"38_CR3","unstructured":"Bi, H., et al.: Motus: A unified latent action world model. arXiv preprint arXiv:2512.13030 (2025)"},{"key":"38_CR4","unstructured":"Blattmann, A., et al.: Stable video diffusion: Scaling latent video diffusion models to large datasets (2023). arXiv:2311.15127"},{"key":"38_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 (2025)","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Chu, R., et al.: Wan-move: Motion-controllable video generation via latent trajectory guidance. In: NeurIPS (2025)","DOI":"10.52202\/085713-0014"},{"key":"38_CR7","unstructured":"Fu, X., et al.: 3dtrajmaster: Mastering 3d trajectory for multi-entity motion in video generation. In: ICLR (2024)"},{"key":"38_CR8","unstructured":"Fung, P., et al.: Embodied ai agents: Modeling the world (2025). arXiv preprint arXiv:2506.22355"},{"key":"38_CR9","unstructured":"Gao, S., et al.: Dreamdojo: A generalist robot world model from large-scale human videos, (2026). arXiv preprint arXiv:2602.06949"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Geng, D., et al.: Motion prompting: Controlling video generation with motion trajectories. In: CVPR, pp. 1\u201312 (2025)","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"38_CR11","unstructured":"Grauman, K., et\u00a0al.: Ego4d: Around the world in 3,000 hours of egocentric video. In: CVPR, pp. 18995\u201319012 (2022)"},{"key":"38_CR12","unstructured":"Hafner, D., Yan, W., Lillicrap, T.: Training agents inside of scalable world models, (2025). arXiv preprint arXiv:2509.24527"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Han, X., Zhu, X., Deng, J., Song, Y.Z., Xiang, T.: Controllable person image synthesis with pose-constrained latent diffusion. In: ICCV, pp. 22768\u201322777 (2023)","DOI":"10.1109\/ICCV51070.2023.02081"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Hassan, M., et al.: Gem: A generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control. In: CVPR, pp. 22404\u201322415. (2025)","DOI":"10.1109\/CVPR52734.2025.02087"},{"key":"38_CR15","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. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"38_CR16","unstructured":"Hoque, R., Huang, P., Yoon, D.J., Sivapurapu, M., Zhang, J.: Egodex: Learning dexterous manipulation from large-scale egocentric video (2025). arXiv preprintarXiv:2505.11709"},{"key":"38_CR17","unstructured":"Hu, E.J., et\u00a0al.: Lora: Low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Jain, Y., Nasery, A., Vineet, V., Behl, H.: Peekaboo: Interactive video generation via masked-diffusion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"38_CR19","unstructured":"Jiang, Y., et al.: Rynnvla-001: Using human demonstrations to improve robot manipulation. arXiv preprint arXiv:2509.15212 (2025)"},{"key":"38_CR20","unstructured":"Jin, Y., et al.: Pyramidal flow matching for efficient video generative modeling. In: ICLR (2025)"},{"key":"38_CR21","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"38_CR22","unstructured":"Lee, Y.C., et al.: Generative video motion editing with 3d point tracks. arXiv preprint arXiv:2512.02015 (2025)"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Li, G., Zhao, B., Yang, J., Sevilla-Lara, L.: Mask2iv: Interaction-centric video generation via mask trajectories (2025). arXiv preprint arXiv:2510.03135","DOI":"10.1609\/aaai.v40i8.37533"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"D Li, Q., Xing, Z., Wang, R., Zhang, H., Dai, Q., Wu, Z.: Magicmotion: Controllable video generation with dense-to-sparse trajectory guidance, (2025). arXiv preprint arXiv:2503.16421","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Image conductor: Precision control for interactive video synthesis. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"38_CR26","unstructured":"Lykov, A., et al.: Physicalagent: Towards general cognitive robotics with foundation world models, (2025). arXiv preprint arXiv:2509.13903"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Ma, W.D.K., Lewis, J.P., Kleijn, W.B.: Trailblazer: Trajectory control for diffusion-based video generation. In: ACM SIGGRAPH Asia, (2024)","DOI":"10.1145\/3680528.3687652"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Mendonca, R., Bahl, S., Pathak, D.: Structured world models from human videos, (2023). arXiv preprint arXiv:2308.10901","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"38_CR29","unstructured":"Namekata, K., Bahmani, S., Wu, Z., Kant, Y., Gilitschenski, I., Lindell, D.B.: Sg-i2v: Self-guided trajectory control in image-to-video generation. In: ICLR (2025)"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Ni, C., et al.: Recondreamer: Crafting world models for driving scene reconstruction via online restoration. arXiv preprint arXiv:2411.19548 (2024)","DOI":"10.1109\/CVPR52734.2025.00153"},{"key":"38_CR31","unstructured":"PAI, A.: Wan2.1-fun control video generation models. HuggingFace Model Collection (2025). https:\/\/huggingface.co\/collections\/alibaba-pai\/wan21-fun-v11"},{"key":"38_CR32","unstructured":"Pallotta, E., Azar, S.M., Doorenbos, L., Ozsoy, S., Iqbal, U., Gall, J.: Egocontrol: Controllable egocentric video generation via 3d full-body poses (2025). arXiv preprint arXiv:2511.18173"},{"key":"38_CR33","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":"38_CR34","doi-asserted-by":"crossref","unstructured":"D Potamias, R.A., Zhang, J., Deng, J., Zafeiriou, S.: Wilor: end-to-end 3D hand localization and reconstruction in-the-wild. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12242\u201312254 (2025)","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"38_CR35","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Dexmv: Imitation learning for dexterous manipulation from human videos. In: European Conference on Computer Vision, pp. 570\u2013587. Springer (2022)","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"38_CR36","unstructured":"Qiu, H., Chen, Z., Wang, Z., He, Y., Xia, M., Liu, Z.: Freetraj: Tuning-free trajectory control in video diffusion models, (2024). arXiv preprint arXiv:2406.16863"},{"key":"38_CR37","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement (2018). arXiv preprint arXiv:1804.02767"},{"key":"38_CR38","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"38_CR39","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: Modeling and capturing hands and bodies together (2022). arXiv preprint arXiv:2201.02610"},{"key":"38_CR40","doi-asserted-by":"crossref","unstructured":"Shi, M., et al.: Egohumanoid: Unlocking in-the-wild loco-manipulation with robot-free egocentric demonstration. arXiv preprint arXiv:2602.10106 (2026)","DOI":"10.15607\/RSS.2026.XXII.204"},{"key":"38_CR41","doi-asserted-by":"crossref","unstructured":"Shi, X., et\u00a0al.: Motion-i2v: Consistent and controllable image-to-video generation with explicit motion modeling. In: ACM SIGGRAPH (2024)","DOI":"10.1145\/3641519.3657497"},{"key":"38_CR42","unstructured":"Shin, J., et al.: Motionstream: Real-time video generation with interactive motion controls, (2025). arXiv preprint arXiv:2511.01266"},{"key":"38_CR43","doi-asserted-by":"crossref","unstructured":"Tu, Y., Luo, H., Chen, X., Bai, X., Wang, F., Zhao, H.: Playerone: Egocentric world simulator (2025). arXiv preprint arXiv:2506.09995","DOI":"10.52202\/085713-4861"},{"key":"38_CR44","unstructured":"Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: FVD a new metric for video generation (2019)"},{"key":"38_CR45","unstructured":"Wan, T., et\u00a0al.: Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"38_CR46","unstructured":"Wang, A., Huang, H., Fang, J.Z., Yang, Y., Ma, C.: ATI: Any trajectory instruction for controllable video generation (2025). arXiv preprint arXiv:2505.22944"},{"key":"38_CR47","doi-asserted-by":"crossref","unstructured":"Wang, B., et al.: Humandreamer: Generating controllable human-motion videos via decoupled generation. arXiv preprint arXiv:2503.24026 (2025)","DOI":"10.1109\/CVPR52734.2025.01156"},{"key":"38_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Cinemaster: A 3d-aware and controllable framework for cinematic text-to-video generation. arXiv preprint arXiv:2502.08639 (2025)","DOI":"10.1145\/3721238.3730755"},{"key":"38_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Videocomposer: Compositional video synthesis with motion controllability. In: NeurIPS (2023)","DOI":"10.52202\/075280-0334"},{"key":"38_CR50","unstructured":"Wang, X., et al.: Replace anyone in videos. arXiv preprint arXiv:2409.19911 (2024)"},{"key":"38_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Precise action-to-video generation through visual action prompts, (2025). arXiv preprint arXiv:2508.13104","DOI":"10.1109\/ICCV51701.2025.01181"},{"key":"38_CR52","unstructured":"Wang, Y., Ouyang, W., Wei, T., Dong, Y., Shen, Z., Pan, X.: Hand2world: Autoregressive egocentric interaction generation via free-space hand gestures, (2026). arXiv preprint arXiv:2602.09600"},{"issue":"4","key":"38_CR53","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"38_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Motionctrl: A unified and flexible motion controller for video generation. In: ACM SIGGRAPH, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"38_CR55","unstructured":"Wu, B., et\u00a0al.: Hunyuanvideo 1.5 technical report. arXiv preprint arXiv:2511.18870 (2025)"},{"key":"38_CR56","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: Draganything: Motion control for anything using entity representation. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"38_CR57","unstructured":"Xia, B., et al.: Dreamve: Unified instruction-based image and video editing (2025). arXiv preprint arXiv:2508.06080"},{"key":"38_CR58","unstructured":"Xiao, Z., et al.: Trajectory attention for fine-grained video motion control. In: ICLR (2025)"},{"key":"38_CR59","doi-asserted-by":"crossref","unstructured":"Xin, C., Yu, M., Jiang, Y., Zhang, Z., Li, X.: Analyzing key objectives in human-to-robot retargeting for dexterous manipulation. IEEE Robotics and Automation Practice, (2026)","DOI":"10.1109\/RAP.2026.3656110"},{"key":"38_CR60","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: Motioncanvas: Cinematic shot design with controllable image-to-video generation. In: ACM SIGGRAPH (2025)","DOI":"10.1145\/3721238.3730604"},{"key":"38_CR61","unstructured":"Zhang, B., Shou, M.Z.: Ego-centric predictive model conditioned on hand trajectories (2025). arXiv preprint arXiv:2508.19852"},{"key":"38_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"38_CR63","unstructured":"Zhang, W., Foo, L.G., Beeler, T., Dabral, R., Theobalt, C.: Vhoi: Controllable video generation of human-object interactions from sparse trajectories via motion densification (2025). arXiv preprint arXiv:2512.09646"},{"key":"38_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Z.,et al.: Tora: Trajectory-oriented diffusion transformer for video generation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00198"},{"key":"38_CR65","unstructured":"Zhao, Z., et al.: Humanoid everyday: A comprehensive robotic dataset for open-world humanoid manipulation (2025). arXiv preprint arXiv:2510.08807"},{"key":"38_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, H., et al.: Trackgo: A flexible and efficient method for controllable video generation. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i10.33167"}],"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\/978-3-032-37038-9_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:43:27Z","timestamp":1789123407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37038-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370372","9783032370389"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37038-9_38","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":"12 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"}}]}}