{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:10:08Z","timestamp":1789038608956,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373922","type":"print"},{"value":"9783032373939","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\/978-3-032-37393-9_12","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:30:49Z","timestamp":1789036249000},"page":"182-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TryOnCrafter: Unleashing Camera Trajectories for\u00a0Realistic Video Virtual Try-on via\u00a0a\u00a0Renderable 4D Try-on Proxy"],"prefix":"10.1007","author":[{"given":"Hao","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanjian","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1331-5020","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsong","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4037-6315","authenticated-orcid":false,"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-2407","authenticated-orcid":false,"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: ReCamMaster: camera-controlled generative rendering from a single video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14834\u201314844 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cao, C., et al.: Uni3C: unifying precisely 3D-enhanced camera and human motion controls for video generation. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201312 (2025)","DOI":"10.1145\/3757377.3763842"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Kwak, S., Lee, K., Choi, H., Shin, J.: Improving diffusion models for authentic virtual try-on in the wild. In: European Conference on Computer Vision, pp. 206\u2013235. Springer (2024)","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"12_CR5","unstructured":"Chong, Z., et al.: CatV2TON: taming diffusion transformers for vision-based virtual try-on with temporal concatenation. arXiv preprint arXiv:2501.11325 (2025)"},{"key":"12_CR6","unstructured":"Fang, Z., et al.: ViViD: video virtual try-on using diffusion models. arXiv preprint arXiv:2405.11794 (2024)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Gong, Y., Song, Y., Li, Y., Li, C., Zhang, Y.: RelationAdapter: learning and transferring visual relation with diffusion transformers. arXiv preprint arXiv:2506.02528 (2025)","DOI":"10.52202\/085713-3255"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Guo, H., Zeng, B., Song, Y., Zhang, W., Zhang, C., Liu, J.: Any2Anytryon: leveraging adaptive position embeddings for versatile virtual clothing tasks. arXiv preprint arXiv:2501.15891 (2025)","DOI":"10.1109\/ICCV51701.2025.01774"},{"key":"12_CR9","unstructured":"He, Het al.: Cameractrl: enabling camera control for text-to-video generation. arXiv preprint arXiv:2404.02101 (2024)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, Z., Chen, P., Wang, G., Li, G., Torr, P.H., Lin, L.: WildviDfit: video virtual try-on in the wild via image-based controlled diffusion models. In: European Conference on Computer Vision. pp. 123\u2013139. Springer (2024)","DOI":"10.1007\/978-3-031-72643-9_8"},{"key":"12_CR11","unstructured":"Hou, C., Chen, Z.: Training-free camera control for video generation. arXiv preprint arXiv:2406.10126 (2024)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S., Song, Y., Zhang, Y., Guo, H., Wang, X., Liu, J.: ArtEditor: learning customized instructional image editor from few-shot examples. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17651\u201317662 (2025)","DOI":"10.1109\/ICCV51701.2025.01640"},{"key":"12_CR13","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, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"12_CR14","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, T., Ho, H.I., Kaufmann, M., Song, J.: PriorAvatar: efficient and robust avatar creation from monocular video using learned priors. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201310 (2025)","DOI":"10.1145\/3757377.3763978"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Karras, J., et al.: Fashion-VDM: video diffusion model for virtual try-on. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687623"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","DOI":"10.1145\/3592433"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Kim, J., Gu, G., Park, M., Park, S., Choo, J.: StableVITON: learning semantic correspondence with latent diffusion model for virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8176\u20138185 (2024)","DOI":"10.1109\/CVPR52733.2024.00781"},{"key":"12_CR19","unstructured":"Li, C., et al.: LatentSync: taming audio-conditioned latent diffusion models for lip sync with syncnet supervision. arXiv preprint arXiv:2412.09262 (2024)"},{"key":"12_CR20","unstructured":"Li, G., et al.: MagicTryon: harnessing diffusion transformer for garment-preserving video virtual try-on. arXiv preprint arXiv:2505.21325 (2025)"},{"key":"12_CR21","doi-asserted-by":"publisher","first-page":"75125","DOI":"10.52202\/079017-2391","volume":"37","author":"X Li","year":"2024","unstructured":"Li, X., et al.: Director3D: real-world camera trajectory and 3D scene generation from text. Adv. Neural. Inf. Process. Syst. 37, 75125\u201375151 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Lin, J., Wu, Y., Wang, Z., Liu, X., Guo, Y.: Pair-ID: a dual modal framework for identity preserving image generation. IEEE Signal Process. Lett. (2024)","DOI":"10.1109\/LSP.2024.3461648"},{"key":"12_CR23","unstructured":"Liu, K., Shao, L., Lu, S.: Novel view extrapolation with video diffusion priors. arXiv preprint arXiv:2411.14208 (2024)"},{"key":"12_CR24","unstructured":"Meng, Y., Zhu, Z., Hui, L., Hou, J.: NVS-solver: video diffusion model as zero-shot novel view synthesizer. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Nguyen, H., Nguyen, Q.Q.V., Nguyen, K., Nguyen, R.: SwiftTry: fast and consistent video virtual try-on with diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 6200\u20136208 (2025)","DOI":"10.1609\/aaai.v39i6.32663"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Qiu, L., et\u00a0al.: LHM: large animatable human reconstruction model from a single image in seconds. arXiv preprint arXiv:2503.10625 (2025)","DOI":"10.1109\/ICCV51701.2025.01316"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Qiu, L., et al.: AniGS: animatable gaussian avatar from a single image with inconsistent gaussian reconstruction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21148\u201321158 (2025)","DOI":"10.1109\/CVPR52734.2025.01970"},{"key":"12_CR28","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Shen, Z., et al.: World-grounded human motion recovery via gravity-view coordinates. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687565"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Song, Q., Lin, M., Zhan, W., Yan, S., Cao, L., Ji, R.: UniVSt: a unified framework for training-free localized video style transfer. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3630010"},{"key":"12_CR31","unstructured":"Song, Q., Lin, Z., Zeng, Z., Zhang, Z., Cao, L., Ji, R.: LightMotion: a light and tuning-free method for simulating camera motion in video generation. arXiv preprint arXiv:2503.06508 (2025)"},{"key":"12_CR32","unstructured":"Song, Q., et al.: FashionChameleon: towards real-time and interactive human-garment video customization. arXiv preprint arXiv:2605.15824 (2026)"},{"key":"12_CR33","unstructured":"Song, Q., Song, Y., Peng, K., Gao, Y., Shou, M.Z.: WorldWander: bridging egocentric and exocentric worlds in video generation. arXiv preprint arXiv:2511.22098 (2025)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Song, Q., et al.: SceneDecorator: towards scene-oriented story generation with scene planning and scene consistency. arXiv preprint arXiv:2510.22994 (2025)","DOI":"10.52202\/085713-2205"},{"key":"12_CR35","unstructured":"Song, Y., Liu, C., Shou, M.Z.: MakeAnything: harnessing diffusion transformers for multi-domain procedural sequence generation. arXiv preprint arXiv:2502.01572 (2025)"},{"key":"12_CR36","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"12_CR39","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Dai, W., Chan, L., Zhou, H., Zhang, A., Liu, S.: GPD-VVTO: preserving garment details in video virtual try-on. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7133\u20137142 (2024)","DOI":"10.1145\/3664647.3680701"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MotionCtrl: a unified and flexible motion controller for video generation. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"12_CR42","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: CAT4D: create anything in 4D with multi-view video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26057\u201326068 (2025)","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"12_CR44","unstructured":"Xiao, Z., et al.: Trajectory attention for fine-grained video motion control. arXiv preprint arXiv:2411.19324 (2024)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gu, T., Chen, W., Chen, A.: OOTDiffusion: outfitting fusion based latent diffusion for controllable virtual try-on. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 8996\u20139004 (2025)","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Tunnel try-on: excavating spatial-temporal tunnels for high-quality virtual try-on in videos. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3199\u20133208 (2024)","DOI":"10.1145\/3664647.3680836"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Yu, M., Hu, W., Xing, J., Shan, Y.: TrajectoryCrafter: redirecting camera trajectory for monocular videos via diffusion models. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 100\u2013111 (2025)","DOI":"10.1109\/ICCV51701.2025.00017"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: ViewCrafter: taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048 (2024)","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"12_CR50","unstructured":"Zhang, J., et al.: MonST3R: a simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:2410.03825 (2024)"},{"key":"12_CR51","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":"12_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Q., Song, Y., Zhang, J., Tang, H., Liu, J.: Stable-hair: Real-world hair transfer via diffusion model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 10348\u201310356 (2025)","DOI":"10.1609\/aaai.v39i10.33123"},{"key":"12_CR53","unstructured":"Zuo, T., et al.: DreamVVT: mastering realistic video virtual try-on in the wild via a stage-wise diffusion transformer framework. arXiv preprint arXiv:2508.02807 (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\/978-3-032-37393-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:31:06Z","timestamp":1789036266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37393-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373922","9783032373939"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37393-9_12","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":"11 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"}}]}}