{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:10:13Z","timestamp":1789161013106,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375520","type":"print"},{"value":"9783032375537","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\/978-3-032-37553-7_22","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:51:37Z","timestamp":1789159897000},"page":"390-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MVI2V: Human Centric Image to\u00a0Video Generation with\u00a0Multiview Consistent Appearance"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiezheng","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"22_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR3","unstructured":"Chen, J.K., Bansal, A., Vo, M.P., Wang, Y.X.: Dress&dance: dress up and dance as you like it-technical preview. arXiv preprint arXiv:2508.21070 (2025)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J.K., Bansal, A., Vo, M.P., Wang, Y.X.: Virtual fitting room: generating arbitrarily long videos of virtual try-on from a single image-technical preview. arXiv preprint arXiv:2509.04450 (2025)","DOI":"10.52202\/085713-5188"},{"key":"22_CR5","unstructured":"Chong, Z., et al.: CatV2TON: taming diffusion transformers for vision-based virtual try-on with temporal concatenation (2025). https:\/\/arxiv.org\/abs\/2501.11325"},{"key":"22_CR6","unstructured":"Gao, Y., et\u00a0al.: SeeDance 1.0: exploring the boundaries of video generation models. arXiv preprint arXiv:2506.09113 (2025)"},{"key":"22_CR7","unstructured":"Gong, L., et al.: AtomoVideo: high fidelity image-to-video generation. ArXiv abs\/2403.01800 (2024)"},{"key":"22_CR8","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. ArXiv abs\/2006.11239 (2020)"},{"key":"22_CR9","unstructured":"Hu, J.E., et al.: LoRA: low-rank adaptation of large language models. ArXiv abs\/2106.09685 (2021)"},{"key":"22_CR10","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). https:\/\/humanaigc.github.io\/animate-anyone\/"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Ju, X., et al.: FullDiT: multi-task video generative foundation model with full attention. arXiv preprint arXiv:2503.19907 (2025)","DOI":"10.1109\/ICCV51701.2025.01460"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"22_CR13","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"22_CR14","unstructured":"Labs, B.F.: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux. Accessed 01 Mar 2026"},{"key":"22_CR15","unstructured":"Li, G., et al.: MagicTryOn: harnessing diffusion transformer for garment-preserving video virtual try-on. arXiv preprint arXiv:2505.21325 (2025)"},{"key":"22_CR16","unstructured":"Lin, B., et al.: Open-sora plan: open-source large video generation model. arXiv preprint arXiv:2412.00131 (2024)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Evaluating text-to-visual generation with image-to-text generation. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"22_CR18","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. ArXiv abs\/2210.02747 (2022)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Phantom: subject-consistent video generation via cross-modal alignment. arXiv preprint arXiv:2502.11079 (2025)","DOI":"10.1109\/ICCV51701.2025.01387"},{"key":"22_CR20","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. ArXiv abs\/2209.03003 (2022)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Peebles, W.S., Xie, S.: Scalable diffusion models with transformers. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4172\u20134182 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR22","unstructured":"Polyak, A., et al.: Movie gen: a cast of media foundation models. arXiv preprint arXiv:2410.13720 (2024)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR24","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"22_CR25","unstructured":"Vaswani, A., et al: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"22_CR26","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"22_CR27","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. ArXiv abs\/2308.06571 (2023)"},{"key":"22_CR28","doi-asserted-by":"crossref","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, pp. 4210\u20134220 (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"22_CR29","unstructured":"Yang, Z., et\u00a0al.: CogVideoX: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Sa2VA: marrying SAM2 with LLaVA for dense grounded understanding of images and videos. ArXiv abs\/2501.04001 (2025)","DOI":"10.1109\/TPAMI.2026.3720379"},{"key":"22_CR31","unstructured":"Zhang, Y., et al.: MimicMotion: high-quality human motion video generation with confidence-aware pose guidance. In: International Conference on Machine Learning (2025)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yuan, Y., Song, Y., Wang, H., Liu, J.: EasyControl: adding efficient and flexible control for diffusion transformer. arXiv preprint arXiv:2503.07027 (2025)","DOI":"10.1109\/ICCV51701.2025.01814"},{"key":"22_CR33","unstructured":"Zheng, D., et al.: VBench-2.0: advancing video generation benchmark suite for intrinsic faithfulness. ArXiv abs\/2503.21755 (2025)"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, Z., Teng, J., Gu, X., Li, C.: Concat-ID: towards universal identity-preserving video synthesis. arXiv preprint arXiv:2503.14151 (2025)","DOI":"10.1109\/ICCVW69036.2025.00202"},{"key":"22_CR35","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: MagicVideo: efficient video generation with latent diffusion models. ArXiv abs\/2211.11018 (2022)"}],"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\/978-3-032-37553-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:51:44Z","timestamp":1789159904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37553-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375520","9783032375537"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37553-7_22","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"}}]}}