Camera-Controlled Video Generation

Overview

Camera-controlled video generation studies how to make a generated or re-shot video follow a desired camera path, from simple pans and orbits to long-horizon navigation. Approaches condition diffusion or autoregressive models on camera poses, geometric cues such as depth and point tracks, or persistent 3D and visual memories; language-based planners can also turn cinematic intent into trajectories. Evaluation increasingly tests camera adherence alongside visual quality, cross-view consistency, and whether scenes remain stable on revisits, using benchmarks with real and synthetic videos. The main tension is that stronger geometric control and long-term consistency can conflict with photorealism, dynamic scene changes, and fast interactive generation.

Latest papers

CardsList

152 papers15 papers in the last four weeks, down 40% on the four weeks before. 0.1% of all new papers.

  1. WorldDraft: If Code Builds the World, Can Video Models Just Render It?

    Nov 12, 2026Zhiyu Hou, Wen-Jie Shu, Harold Haodong Chen +7Video GenerationPhysical Consistency in Video Generation

  2. UGG: Unified Generative Geometry Model

    Nov 10, 2026Amani Kiruga, Zhiyi Li, Ruojin Cai +44D Scene UnderstandingCamera Pose Estimation

  3. WanderBench: Can World Models Explore Dynamic Worlds from Video?

    Nov 9, 2026Yuhang Chen, Jiheng Li, Jiale Wang +2Video World ModelsWorld Model Evaluation

  4. Designing with Cinematic Language: An Intent-Driven Approach to Human-AI Video Clip Co-Creation

    Nov 5, 2026Yi He, Zhengxi Yu, Feilin Han +3Human-AI Co-CreationControllable Video Generation

  5. TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds

    Nov 4, 2026Jiaao Yu, Yanjian Zhang, Haoyang Jiang +3Controllable Video GenerationReal-Time Interactive Video Generation

  6. GSExplorer: Interactive World Generation with a Persistent 3D Gaussian World State

    Nov 1, 2026Sicheng Yu, Liu Liu, Xinjie Wang +73D-Aware Video GenerationVideo World Models

  7. UniCaMo: Unified Camera and Motion Control for Video Diffusion Models

    Oct 31, 2026Long Vu, Tan Ngo, Animesh Karnewar +5Controllable Video GenerationCamera-Controlled Video Generation

  8. Hierarchical Diffusion for Camera-controlled Autoregressive Video Generation

    Oct 27, 2026Kaihua Chen, Yiming Gong, Deva Ramanan +1Camera-Controlled Video GenerationLong-Horizon Video Generation

  9. Hy-Nomas: Towards Free-form Interactive World Generation

    Oct 27, 2026Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng +35Interactive World ModelsVideo Generation

  10. Distilling Dense Trajectory Teachers For Large-Motion Video World Models

    Oct 24, 2026Shuofeng Sun, Linqing Zhao, Haibin YanVideo World ModelsCamera-Controlled Video Generation

  11. WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control

    Oct 23, 2026Lei Cao, Yu Liu, Wenhua Liao +7Video GenerationCamera-Controlled Video Generation

  12. WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models

    Oct 22, 2026Chenxi Song, Yanming Yang, Tong Zhao +3Camera-Controlled Video GenerationTrajectory-Guided Video Generation

  13. UniState: Unifying Memory and Intervention for Controllable World Simulation

    Oct 18, 2026Jaeseok Jeong, Kyungmook Choi, Sohyun Chung +2Controllable Video GenerationVideo World Models

  14. Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion

    Oct 18, 2026Yushi Lan, Zeren Jiang, Koichi Namekata +3Camera-Controlled Video GenerationDynamic Novel View Synthesis

  15. Map2Vid: Embodied Navigation Video Generation with Human-Friendly Motion Control

    Oct 18, 2026Yulin Dai, Yuqian Fu, Tianwen Qian +3Controllable Video GenerationCamera-Controlled Video Generation

  16. Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars

    Oct 16, 2026Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld +33D Avatar GenerationHuman Avatar Animation

  17. Momentum: Persistent Dynamics for Video World Models

    Oct 16, 2026Nedko Savov, Stefan Maria Ailuro, Danda Pani Paudel +3Video World ModelsMemory-Augmented Video Generation

  18. 4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling

    Oct 13, 2026Jianhui Zhang, Zuyao Lin, Pengxin Xu +2Video World ModelsMemory-Augmented Video Generation

  19. World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models

    Oct 12, 2026Junyi Wu, Zekun Li, Chenhongyi Yang +9Video World ModelsMemory-Augmented Video Generation

  20. Totem: Object-Centric 3D Memory for World-Consistent Video Generation

    Oct 11, 2026Zichen Wan, Tianyu Huang, Fan Li +33D-Aware Video GenerationVideo World Models

  21. SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation

    Oct 6, 2026Yunheng Liu, Ziqi Cai, Siqi Yang +7Video GenerationVideo World Models

  22. ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections

    Oct 5, 2026Xiaoyu Zhou, Dingwei Xian, Zhenyu Wang +3Camera-Controlled Video GenerationMulti-View Video Generation

  23. Keepsake: Selective Spatial Memory for Long-Horizon Video Generation

    Oct 5, 2026Abdul Mohaimen Al Radi, Kunyang Li, Yuzhang Shang +2Camera-Controlled Video GenerationLong-Horizon Video Generation

  24. SemCam: Semantic Camera Motion Control for Video Generation

    Oct 4, 2026Janna Bruner, Omer Talmi, Ianir Ideses +3Video-Reference Video GenerationCamera-Controlled Video Generation

  25. LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation

    Oct 2, 2026Ziqi Ma, Shreya Sharma, Mohamed El Banani +8Camera-Controlled Video GenerationLong-Horizon Video Generation