{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T20:31:29Z","timestamp":1789504289543,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":123,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_12","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:30:35Z","timestamp":1788985835000},"page":"203-224","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AnchorWeave: World-Consistent Video Generation with\u00a0Retrieved Local Spatial Memories"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9502-050X","authenticated-orcid":false,"given":"Zun","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1303-8636","authenticated-orcid":false,"given":"Han","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-9590","authenticated-orcid":false,"given":"Jaehong","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-6169","authenticated-orcid":false,"given":"Jaemin","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-6536","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2965-5354","authenticated-orcid":false,"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: AC3D: analyzing and improving 3D camera control in video diffusion transformers (2024). arXiv preprint arXiv:2411.18673","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"12_CR2","unstructured":"Bahmani, S., et al.: VD3D: taming large video diffusion transformers for 3D camera control (2024). arXiv preprint arXiv:2407.12781"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: ReCamMaster: camera-controlled generative rendering from a single video (2025). arXiv preprint arXiv:2503.11647","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"12_CR4","unstructured":"Bai, J., et al.: SynCamMaster: synchronizing multi-camera video generation from diverse viewpoints. In: Proceedings ICLR (2025)"},{"key":"12_CR5","unstructured":"Ball, P.J., et al.: Genie 3: a new frontier for world models. Google DeepMind (2025). https:\/\/deepmind.google\/blog\/genie-3-a-new-frontier-for-world-models\/"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Bernal-Berdun, E., et al.: PreciseCam: precise camera control for text-to-image generation (2025). arXiv preprint arXiv:2501.12910","DOI":"10.1109\/CVPR52734.2025.00260"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Bian, W., Huang, Z., Shi, X., Li, Y., Wang, F.Y., Li, H.: GS-DiT: advancing video generation with pseudo 4D Gaussian fields through efficient dense 3D point tracking (2025). arXiv preprint arXiv:2501.02690","DOI":"10.1109\/CVPR52734.2025.02023"},{"key":"12_CR8","unstructured":"Bruce, J., et\u00a0al.: Genie: generative interactive environments. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Burgert, R., et al.: Go-with-the-flow: motion-controllable video diffusion models using real-time warped noise. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13\u201323 (2025)","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Cao, C., et al.: Uni3C: unifying precisely 3D-enhanced camera and human motion controls for video generation (2025). arXiv preprint arXiv:2504.14899","DOI":"10.1145\/3757377.3763842"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Chen, B., Mart\u00ed Mons\u00f3, D., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. In: Advances in Neural Information Processing Systems, vol. 37, pp. 24081\u201324125 (2024)","DOI":"10.52202\/079017-0759"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Chen, B., Mons\u00f3, D.M., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/079017-0759"},{"key":"12_CR13","unstructured":"Chen, H., Xu, C., Yang, X., Chen, X., Deng, C.: Past-and future-informed KV cache policy with salience estimation in autoregressive video diffusion (2026). arXiv preprint arXiv:2601.21896"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Chen, T., Hu, X., Ding, Z., Jin, C.: Learning world models for interactive video generation (2025). arXiv preprint arXiv:2505.21996","DOI":"10.52202\/085713-5166"},{"key":"12_CR15","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: TTT3R: 3D reconstruction as test-time training (2025). arXiv preprint arXiv:2509.26645"},{"key":"12_CR16","unstructured":"Chen, Y., et al.: PostCam: camera-controllable novel-view video generation with query-shared cross-attention (2025). arXiv preprint arXiv:2511.17185"},{"key":"12_CR17","unstructured":"Chou, Y.C., et al.: Captain safari: a world engine (2025). arXiv preprint arXiv:2511.22815"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Dalal, K., et al.: One-minute video generation with test-time training. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17702\u201317711 (2025)","DOI":"10.1109\/CVPR52734.2025.01649"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: OBJAVERSE: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"12_CR20","unstructured":"Feng, W., et al.: I2VControl-camera: precise video camera control with adjustable motion strength (2024). arXiv preprint arXiv:2411.06525"},{"key":"12_CR21","unstructured":"Fortier-Chouinard, F., Hold-Geoffroy, Y., Deschaintre, V., Gadelha, M., Lalonde, J.F.: GimbalDiffusion: gravity-aware camera control for video generation (2025). arXiv preprint arXiv:2512.09112"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: CAT3D: create anything in 3D with multi-view diffusion models. In: Proceedings NeurIPS (2024)","DOI":"10.52202\/079017-2403"},{"key":"12_CR23","unstructured":"Greff, K., et\u00a0al.: Kubric: a scalable dataset generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3749\u20133761 (2022)"},{"key":"12_CR24","unstructured":"Gu, Y., Mao, W., Shou, M.Z.: Long-context autoregressive video modeling with next-frame prediction (2025). arXiv preprint arXiv:2503.19325"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Gu, Z., et\u00a0al.: Diffusion as Shader: 3D-aware video diffusion for versatile video generation control (2025). arXiv preprint arXiv:2501.03847","DOI":"10.1145\/3721238.3730607"},{"key":"12_CR26","unstructured":"Guo, X., Ding, C., Dou, H., Zhang, X., Tang, W., Wu, W.: InfinityDrive: breaking time limits in driving world models (2024). arXiv preprint arXiv:2412.01522"},{"key":"12_CR27","unstructured":"Guo, Y., Shi, L.X., Chen, J., Finn, C.: CTRL-WORLD: a controllable generative world model for robot manipulation (2025). arXiv preprint arXiv:2510.10125"},{"key":"12_CR28","unstructured":"HaCohen, Y., et\u00a0al.: LTX-2: efficient joint audio-visual foundation model (2026). arXiv preprint arXiv:2601.03233"},{"key":"12_CR29","unstructured":"He, H., et al.: CameraCtrl: enabling camera control for text-to-video generation (2024). arXiv preprint arXiv:2404.02101"},{"key":"12_CR30","unstructured":"He, H., et al.: CameraCtrl: enabling camera control for video diffusion models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"He, H., et al.: CameraCtrl II: dynamic scene exploration via camera-controlled video diffusion models (2025). arXiv preprint arXiv:2503.10592","DOI":"10.1109\/ICCV51701.2025.01246"},{"key":"12_CR32","unstructured":"He, X., et al.: Matrix-game 2.0: an open-source real-time and streaming interactive world model (2025). arXiv preprint arXiv:2508.13009"},{"key":"12_CR33","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"12_CR34","unstructured":"Hong, Y., et\u00a0al.: RELIC: interactive video world model with long-horizon memory (2025). arXiv preprint arXiv:2512.04040"},{"key":"12_CR35","unstructured":"Hong, Y., et\u00a0al.: SlowFast-VGen: slow-fast learning for action-driven long video generation (2024). arXiv preprint arXiv:2410.23277"},{"key":"12_CR36","unstructured":"Hou, C., Wei, G., Zeng, Y., Chen, Z.: Training-free camera control for video generation (2024). arXiv preprint arXiv:2406.10126"},{"key":"12_CR37","unstructured":"Hou, Y., Zheng, L., Torr, P.: Learning camera movement control from real-world drone videos (2024). arXiv preprint arXiv:2412.09620"},{"key":"12_CR38","unstructured":"Hu, T., Peng, H., Liu, X., Ma, Y.: EX-4D: extreme viewpoint 4D video synthesis via depth watertight mesh (2025). arXiv preprint arXiv:2506.05554"},{"issue":"6","key":"12_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3763330","volume":"44","author":"T Huang","year":"2025","unstructured":"Huang, T., et al.: Voyager: long-range and world-consistent video diffusion for explorable 3D scene generation. ACM Trans. Graph. (TOG) 44(6), 1\u201315 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion (2025). arXiv preprint arXiv:2506.08009","DOI":"10.52202\/085713-5576"},{"key":"12_CR41","unstructured":"Huang, Z., et al.: SpaceTimePilot: generative rendering of dynamic scenes across space and time (2025). arXiv preprint arXiv:2512.25075"},{"key":"12_CR42","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_CR43","doi-asserted-by":"crossref","unstructured":"Jin, W., Dai, Q., Luo, C., Baek, S.H., Cho, S.: FloVD: optical flow meets video diffusion model for enhanced camera-controlled video synthesis (2025). arXiv preprint arXiv:2502.08244","DOI":"10.1109\/CVPR52734.2025.00196"},{"key":"12_CR44","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: a systematic framework for large video generative models (2024). arXiv preprint arXiv:2412.03603"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Lin, B.J., Sun, W.F., Lee, C.Y.: Enhancing memory and imagination consistency in diffusion-based world models via linear-time sequence modeling. arXiv e-prints, pp. arXiv 2502 (2025)","DOI":"10.52202\/085713-3526"},{"key":"12_CR46","unstructured":"Lee, J., et al.: 3D scene prompting for scene-consistent camera-controllable video generation (2025). arXiv preprint arXiv:2510.14945"},{"key":"12_CR47","unstructured":"Li, G., et al.: MagicWorld: interactive geometry-driven video world exploration (2025). arXiv preprint arXiv:2511.18886"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: NVComposer: boosting generative novel view synthesis with multiple sparse and unposed images (2024). arXiv preprint arXiv:2412.03517","DOI":"10.1109\/CVPR52734.2025.00081"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Li, R., Torr, P., Vedaldi, A., Jakab, T.: VMem: consistent interactive video scene generation with surfel-indexed view memory (2025). arXiv preprint arXiv:2506.18903","DOI":"10.1109\/ICCV51701.2025.02383"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Li, T., et\u00a0al.: RealCam-I2V: real-world image-to-video generation with interactive complex camera control (2025). arXiv preprint arXiv:2502.10059","DOI":"10.1109\/ICCV51701.2025.02673"},{"key":"12_CR51","unstructured":"Li, Y., et al.: ReCamDriving: LiDAR-free camera-controlled novel trajectory video generation (2025). arXiv preprint arXiv:2512.03621"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: WonderPlay: dynamic 3D scene generation from a single image and actions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.00849"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Liang, H., et al.: Wonderland: navigating 3D scenes from a single image. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 798\u2013810 (2025)","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"12_CR54","unstructured":"Liao, K., et al.: Thinking with camera: a unified multimodal model for camera-centric understanding and generation (2025). arXiv preprint arXiv:2510.08673"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: DL3DV-10K: a large-scale scene dataset for deep learning-based 3D vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22160\u201322169 (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"12_CR56","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"12_CR57","unstructured":"Liu, F., et al.: ReconX: reconstruct any scene from sparse views with video diffusion model (2024). arXiv preprint arXiv:2408.16767"},{"key":"12_CR58","unstructured":"Liu, K., Hu, W., Xu, J., Shan, Y., Lu, S.: Rolling forcing: autoregressive long video diffusion in real time (2025). arXiv preprint arXiv:2509.25161"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Liu, P., et al.: DynaMem: online dynamic spatio-semantic memory for open world mobile manipulation. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 13346\u201313355. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127619"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Lu, D., et al.: See4D: pose-free 4D generation via auto-regressive video inpainting (2025). arXiv preprint arXiv:2510.26796","DOI":"10.1111\/cgf.70345"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: CamCloneMaster: enabling reference-based camera control for video generation. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201310 (2025)","DOI":"10.1145\/3757377.3763841"},{"key":"12_CR62","unstructured":"Ma, Y., et\u00a0al.: Flow caching for autoregressive video generation (2026). arXiv preprint arXiv:2602.10825"},{"key":"12_CR63","unstructured":"Mao, X., et al.: Yume-1.5: a text-controlled interactive world generation model (2025). arXiv preprint arXiv:2512.22096"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., et al.: MultiDiff: consistent novel view synthesis from a single image. In: Proceedings CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"12_CR65","unstructured":"Pan, P., et\u00a0al.: Diff4Splat: controllable 4D scene generation with latent dynamic reconstruction models (2025). arXiv preprint arXiv:2511.00503"},{"key":"12_CR66","unstructured":"Park, J., Kwon, T., Ye, J.C.: Zero4D: training-free 4D video generation from single video using off-the-shelf video diffusion (2025). arXiv preprint arXiv:2503.22622"},{"key":"12_CR67","unstructured":"Parker-Holder, J., et al.: Genie 2: a large-scale foundation world model. Google DeepMind (2024). https:\/\/deepmind.google\/discover\/blog\/genie-2-a-large-scale-foundation-world-model\/"},{"key":"12_CR68","doi-asserted-by":"crossref","unstructured":"Po, R., et al.: Long-context state-space video world models (2025). arXiv preprint arXiv:2505.20171","DOI":"10.1109\/ICCV51701.2025.00817"},{"key":"12_CR69","doi-asserted-by":"crossref","unstructured":"Popov, S., Raj, A., Krainin, M., Li, Y., Freeman, W.T., Rubinstein, M.: CamCtrl3D: single-image scene exploration with precise 3D camera control (2025). arXiv preprint arXiv:2501.06006","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"12_CR70","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":"12_CR71","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR72","unstructured":"Samuel, D., Tzachor, I., Levy, M., Green, M., Chechik, G., Ben-Ari, R.: Fast autoregressive video diffusion and world models with temporal cache compression and sparse attention (2026). arXiv preprint arXiv:2602.01801"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Savov, N., Kazemi, N., Zhang, D., Paudel, D.P., Wang, X., Van Gool, L.: StateSpaceDiffuser: bringing long context to diffusion world models (2025). arXiv preprint arXiv:2505.22246","DOI":"10.52202\/085713-2316"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Seo, J., et al.: GenWarp: single image to novel views with semantic-preserving generative warping. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-2550"},{"key":"12_CR75","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). arXiv preprint arXiv:2509.15130"},{"key":"12_CR76","unstructured":"Song, K., Chen, B., Simchowitz, M., Du, Y., Tedrake, R., Sitzmann, V.: History-guided video diffusion (2025). arXiv preprint arXiv:2502.06764"},{"key":"12_CR77","doi-asserted-by":"crossref","unstructured":"Sun, W., et al.: DimensionX: create any 3D and 4D scenes from a single image with controllable video diffusion (2024). arXiv preprint arXiv:2411.04928","DOI":"10.1109\/ICCV51701.2025.01271"},{"key":"12_CR78","unstructured":"Sun, W., et al.: WorldPlay: towards long-term geometric consistency for real-time interactive world modeling (2025). arXiv preprint arXiv:2512.14614"},{"key":"12_CR79","unstructured":"Team, R., et\u00a0al.: Advancing open-source world models (2026). arXiv preprint arXiv:2601.20540"},{"key":"12_CR80","unstructured":"Van\u00a0Hoorick, B., et al.: AnyView: synthesizing any novel view in dynamic scenes (2026). arXiv preprint arXiv:2601.16982"},{"key":"12_CR81","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":"12_CR82","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models (2025). arXiv preprint arXiv:2503.20314"},{"key":"12_CR83","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: 4Real-Video: learning generalizable photo-realistic 4D video diffusion (2024). arXiv preprint arXiv:2412.04462","DOI":"10.1109\/CVPR52734.2025.01651"},{"key":"12_CR84","unstructured":"Wang, Z., et\u00a0al.: WorldCompass: reinforcement learning for long-horizon world models (2026). arXiv preprint arXiv:2602.09022"},{"key":"12_CR85","unstructured":"Wang, Z., et al.: Taming camera-controlled video generation with verifiable geometry reward (2025). arXiv preprint arXiv:2512.02870"},{"key":"12_CR86","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_CR87","unstructured":"Wang, Z., et al.: EPiC: efficient video camera control learning with precise anchor-video guidance (2025). arXiv preprint arXiv:2505.21876"},{"key":"12_CR88","unstructured":"Watson, D., Saxena, S., Li, L., Tagliasacchi, A., Fleet, D.J.: Controlling space and time with diffusion models. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"12_CR89","unstructured":"Wu, H., et al.: Geometry forcing: marrying video diffusion and 3D representation for consistent world modeling (2025). arXiv preprint arXiv:2507.07982"},{"key":"12_CR90","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: CAT4D: create anything in 4D with multi-view video diffusion models. In: Proceedings CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"12_CR91","unstructured":"Wu, T., et al.: Video world models with long-term spatial memory (2025). https:\/\/arxiv.org\/abs\/2506.05284"},{"key":"12_CR92","unstructured":"Wu, X., Zhang, G., Xu, Z., Zhou, Y., Lu, Q., He, X.: Pack and force your memory: long-form and consistent video generation (2025). arXiv preprint arXiv:2510.01784"},{"key":"12_CR93","unstructured":"Xiang, J., et\u00a0al.: PAN: a world model for general, interactable, and long-horizon world simulation (2025). arXiv preprint arXiv:2511.09057"},{"key":"12_CR94","doi-asserted-by":"crossref","unstructured":"Xiao, Z., et al.: WorldMem: long-term consistent world simulation with memory (2025). arXiv preprint arXiv:2504.12369","DOI":"10.52202\/085713-1659"},{"key":"12_CR95","unstructured":"Xiao, Z., et al.: Trajectory attention for fine-grained video motion control (2024). arXiv preprint arXiv:2411.19324"},{"key":"12_CR96","unstructured":"Xiao, Z., et al.: Video4Spatial: towards visuospatial intelligence with context-guided video generation (2025). arXiv preprint arXiv:2512.03040"},{"key":"12_CR97","unstructured":"Xie, M., et al.: LaVR: scene latent conditioned generative video trajectory re-rendering using large 4D reconstruction models (2026). arXiv preprint arXiv:2601.14674"},{"key":"12_CR98","unstructured":"Xu, D., et al.: CamCo: camera-controllable 3D-consistent image-to-video generation (2024). arXiv preprint arXiv:2406.02509"},{"key":"12_CR99","unstructured":"Yang, S., et al.: LongLive: real-time interactive long video generation (2025). arXiv preprint arXiv:2509.22622"},{"key":"12_CR100","unstructured":"Yang, X., et\u00a0al.: OmniCam: unified multimodal video generation via camera control (2025). arXiv preprint arXiv:2504.02312"},{"key":"12_CR101","unstructured":"Yang, Y., Fan, L., Shi, Z., Peng, J., Wang, F., Zhang, Z.: NeoVerse: enhancing 4D world model with in-the-wild monocular videos (2026). arXiv preprint arXiv:2601.00393"},{"key":"12_CR102","unstructured":"Yang, Z., et\u00a0al.: CogVideoX: text-to-video diffusion models with an expert transformer (2024). arXiv preprint arXiv:2408.06072"},{"key":"12_CR103","unstructured":"Ye, D., et\u00a0al.: Yan: foundational interactive video generation (2025). arXiv preprint arXiv:2508.08601"},{"key":"12_CR104","unstructured":"You, M., Zhu, Z., Liu, H., Hou, J.: NVS-Solver: Video diffusion model as zero-shot novel view synthesizer (2024). arXiv preprint arXiv:2405.15364"},{"key":"12_CR105","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: 4Real: towards photorealistic 4D scene generation via video diffusion models. In: Advances in Neural Information Processing Systems, vol. 37, pp. 45256\u201345280 (2024)","DOI":"10.52202\/079017-1438"},{"key":"12_CR106","doi-asserted-by":"crossref","unstructured":"Yu, H.X., Duan, H., Herrmann, C., Freeman, W.T., Wu, J.: WonderWorld: interactive 3D scene generation from a single image. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5916\u20135926 (2025)","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"12_CR107","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Context as memory: scene-consistent interactive long video generation with memory retrieval. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763833"},{"key":"12_CR108","doi-asserted-by":"crossref","unstructured":"YU, M., Hu, W., Xing, J., Shan, Y.: TrajectoryCrafter: redirecting camera trajectory for monocular videos via diffusion models (2025). arXiv preprint arXiv:2503.05638","DOI":"10.1109\/ICCV51701.2025.00017"},{"key":"12_CR109","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: ViewCrafter: taming video diffusion models for high-fidelity novel view synthesis (2024). arXiv preprint arXiv:2409.02048","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"12_CR110","unstructured":"Yu, W., Yin, S., Easterbrook, S., Garg, A.: EgoSim: egocentric exploration in virtual worlds with multi-modal conditioning. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=zAyS5aRKV8"},{"key":"12_CR111","unstructured":"Zhang, C., et al.: Unified camera positional encoding for controlled video generation (2025). arXiv preprint arXiv:2512.07237"},{"key":"12_CR112","doi-asserted-by":"crossref","unstructured":"Zhang, D.J., et al.: ReCapture: generative video camera controls for user-provided videos using masked video fine-tuning (2024). arXiv preprint arXiv:2411.05003","DOI":"10.1109\/CVPR52734.2025.00197"},{"key":"12_CR113","doi-asserted-by":"crossref","unstructured":"Zhang, L., Cai, S., Li, M., Wetzstein, G., Agrawala, M.: Frame context packing and drift prevention in next-frame-prediction video diffusion models. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-1024"},{"key":"12_CR114","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: World-consistent video diffusion with explicit 3D modeling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21685\u201321695 (2025)","DOI":"10.1109\/CVPR52734.2025.02020"},{"key":"12_CR115","unstructured":"Zhang, T., et al.: Test-time training done right (2025). arXiv preprint arXiv:2505.23884"},{"key":"12_CR116","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Chen, D., Liao, J.: I2V3D: controllable image-to-video generation with 3D guidance (2025). arXiv preprint arXiv:2503.09733","DOI":"10.1109\/ICCV51701.2025.01241"},{"key":"12_CR117","unstructured":"Zhao, J., Wei, F., Liu, Z., Zhang, H., Xu, C., Lu, Y.: Spatia: Video generation with updatable spatial memory (2025). arXiv preprint arXiv:2512.15716"},{"key":"12_CR118","unstructured":"Zheng, G., Li, T., Jiang, R., Lu, Y., Wu, T., Li, X.: Cami2V: camera-controlled image-to-video diffusion model (2024). arXiv preprint arXiv:2410.15957"},{"key":"12_CR119","unstructured":"Zheng, S., et al.: VidCRAFT3: camera, object, and lighting control for image-to-video generation (2025). arXiv preprint arXiv:2502.07531"},{"key":"12_CR120","doi-asserted-by":"crossref","unstructured":"Zhou, J.J., et al.: Stable virtual camera: generative view synthesis with diffusion models. arXiv e-prints, p. 2503 (2025)","DOI":"10.1109\/ICCV51701.2025.01153"},{"key":"12_CR121","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Learning 3D persistent embodied world models (2025). arXiv preprint arXiv:2505.05495","DOI":"10.52202\/085713-3501"},{"key":"12_CR122","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images (2018). arXiv preprint arXiv:1805.09817","DOI":"10.1145\/3197517.3201323"},{"key":"12_CR123","doi-asserted-by":"crossref","unstructured":"Zhou, Z., An, J., Luo, J.: Latent-reframe: enabling camera control for video diffusion model without training (2024). arXiv preprint arXiv:2412.06029","DOI":"10.1109\/ICCV51701.2025.01187"}],"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\/978-3-032-37356-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:31:07Z","timestamp":1788985867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":123,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_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":"10 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"}}]}}