{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:09:43Z","timestamp":1789117783073,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371669","type":"print"},{"value":"9783032371676","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\/978-3-032-37167-6_20","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:46:37Z","timestamp":1789116397000},"page":"354-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MoCam: Unified Novel View Synthesis via\u00a0Structured Denoising Dynamics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1776-8952","authenticated-orcid":false,"given":"Haofeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5708-0959","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"20_CR1","unstructured":"Bahmani, S., et al.: Vd3d: taming large video diffusion transformers for 3d camera control. arXiv:2407.12781 arXiv preprint (2024)"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: Recammaster: camera-controlled generative rendering from a single video. arXiv preprint arXiv:2503.11647 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"20_CR3","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv:2311.15127 arXiv preprint (2023)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Cao, A., Johnson, J.: Hexplane: a fast representation for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 130\u2013141 (2023)","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., Khurana, T., Ramanan, D.: Reconstruct, inpaint, finetune: dynamic novel-view synthesis from monocular videos. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-1592"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Chung, J., Lee, S., Nam, H., Lee, J., Lee, K.M.: Luciddreamer: domain-free generation of 3d gaussian splatting scenes. IEEE Trans. Visual. Comput. Graph. (2025)","DOI":"10.1109\/TVCG.2025.3611489"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Duan, Y., Wei, F., Dai, Q., He, Y., Chen, W., Chen, B.: 4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657463"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Fan, C.D., et al.: Spectromotion: dynamic 3d reconstruction of specular scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21328\u201321338 (2025)","DOI":"10.1109\/CVPR52734.2025.01987"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Meanti, G., Warburg, F.R., Recht, B., Kanazawa, A.: K-planes: explicit radiance fields in space, time, and appearance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12479\u201312488 (2023)","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Gao, C., Saraf, A., Kopf, J., Huang, J.B.: Dynamic view synthesis from dynamic monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5712\u20135721 (2021)","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Gao, H., Li, R., Tulsiani, S., Russell, B., Kanazawa, A.: Dynamic novel-view synthesis: a reality check. In: NeurIPS (2022)","DOI":"10.52202\/068431-2447"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Ham, S., Woo, S., Kim, J.Y., Go, H., Park, B., Kim, C.: Diffusion model patching via mixture-of-prompts. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 17023\u201317031 (2025)","DOI":"10.1609\/aaai.v39i16.33871"},{"key":"20_CR13","unstructured":"He, H., et al.: Cameractrl: enabling camera control for text-to-video generation. arXiv:2404.02101 arXiv preprint (2024)"},{"key":"20_CR14","unstructured":"Huang, J., et al.: Vipe: video pose engine for 3d geometric perception. arXiv:2508.10934 arXiv preprint (2025)"},{"key":"20_CR15","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 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Jeong, H., Lee, S., Ye, J.C.: Reangle-a-video: 4d video generation as video-to-video translation. arXiv:2503.09151 arXiv preprint (2025)","DOI":"10.1109\/ICCV51701.2025.01039"},{"issue":"4","key":"20_CR17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","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)","journal-title":"ACM Trans. Graph."},{"key":"20_CR18","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Lei, G., Wang, C., Wang, Y., Li, H., Song, Y., Xu, W.: Motionflow: learning implicit motion flow for complex camera trajectory control in video generation. arXiv preprint arXiv:2509.21119 (2025)","DOI":"10.1109\/ICME59968.2025.11209460"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Neural 3d video synthesis from multi-view video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5521\u20135531 (2022)","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Li, Z., Xu, Y.: Spacetime gaussian feature splatting for real-time dynamic view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8508\u20138520 (2024)","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6498\u20136508 (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Lin, Y., Dai, Z., Zhu, S., Yao, Y.: Gaussian-flow: 4d reconstruction with dynamic 3d gaussian particle. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21136\u201321145 (2024)","DOI":"10.1109\/CVPR52733.2024.01997"},{"key":"20_CR24","unstructured":"LIU, Q., et al.: MoDGS: dynamic gaussian splatting from casually-captured monocular videos with depth priors. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=2prShxdLkX"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Luo, Z., Ran, H., Lu, L.: Instant4d: 4d gaussian splatting in minutes. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-1005"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. In: European Conference on Computer Vision, pp. 405\u2013421. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"20_CR28","unstructured":"Nan, K., et al.: Openvid-1m: a large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371 (2024)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-nerf: neural radiance fields for dynamic scenes. 2021 IEEE. In: CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10313\u201310322 (2020)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Ren, X., et al.: Gen3c: 3d-informed world-consistent video generation with precise camera control. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6121\u20136132 (2025)","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Shriram, J., Trevithick, A., Liu, L., Ramamoorthi, R.: Realmdreamer: text-driven 3d scene generation with inpainting and depth diffusion. In: 2025 International Conference on 3D Vision (3DV), pp. 882\u2013892. IEEE (2025)","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Song, R., et al.: Coda-4dgs: dynamic gaussian splatting with context and deformation awareness for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 28031\u201328041 (2025)","DOI":"10.1109\/ICCV51701.2025.02602"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Van Hoorick, B., et al.: Generative camera dolly: extreme monocular dynamic novel view synthesis. In: European Conference on Computer Vision, pp. 313\u2013331. Springer (2024)","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"20_CR34","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, Y., Liu, Z., Wang, W., Dong, Z., Yang, B.: Vistadream: sampling multiview consistent images for single-view scene reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26772\u201326782 (2025)","DOI":"10.1109\/ICCV51701.2025.02485"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4d gaussian splatting for real-time dynamic scene rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Wu, P., et al.: Improved video VAE for latent video diffusion model. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18124\u201318133 (2025)","DOI":"10.1109\/CVPR52734.2025.01689"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: Cat4d: create anything in 4d with multi-view video diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26057\u201326068 (2025)","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"20_CR39","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhang, L.: Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting. arXiv preprint arXiv:2310.10642 (2023)"},{"key":"20_CR40","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20331\u201320341 (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"20_CR42","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv:2308.06721 arXiv preprint (2023)"},{"key":"20_CR43","unstructured":"You, M., Zhu, Z., Liu, H., Hou, J.: NVS-solver: video diffusion model as zero-shot novel view synthesizer. arXiv:2405.15364 arXiv preprint (2024)"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"YU, M., Hu, W., Xing, J., Shan, Y.: Trajectorycrafter: redirecting camera trajectory for monocular videos via diffusion models. arXiv preprint arXiv:2503.05638 (2025)","DOI":"10.1109\/ICCV51701.2025.00017"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Viewcrafter: taming video diffusion models for high-fidelity novel view synthesis. IEEE Trans. Patt. Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: Recapture: generative video camera controls for user-provided videos using masked video fine-tuning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2050\u20132062 (2025)","DOI":"10.1109\/CVPR52734.2025.00197"},{"issue":"12","key":"20_CR47","doi-asserted-by":"publisher","first-page":"7749","DOI":"10.1109\/TVCG.2024.3361502","volume":"30","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Li, X., Wan, Z., Wang, C., Liao, J.: Text2nerf: text-driven 3d scene generation with neural radiance fields. IEEE Trans. Visual Comput. Graphics 30(12), 7749\u20137762 (2024)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Spatialcrafter: unleashing the imagination of video diffusion models for scene reconstruction from limited observations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 27794\u201327805 (2025)","DOI":"10.1109\/ICCV51701.2025.02580"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Mega: memory-efficient 4d gaussian splatting for dynamic scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 27828\u201327838 (2025)","DOI":"10.1109\/ICCV51701.2025.02583"},{"key":"20_CR51","unstructured":"Zhu, J., Tang, H.: Dynamic scene reconstruction: recent advance in real-time rendering and streaming. arXiv:2503.08166 arXiv preprint (2025)"},{"key":"20_CR52","unstructured":"Zhuang, S., et al.: Timestep master: asymmetrical mixture of timestep lora experts for versatile and efficient diffusion models in vision. arXiv preprint arXiv:2503.07416 (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\/978-3-032-37167-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:47:01Z","timestamp":1789116421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37167-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371669","9783032371676"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37167-6_20","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"}}]}}