Research map / Video / Video generation
OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
Yukun Wang, Ruihuang Li, Jiale Tao, Shiyuan Yang, Liyi Chen, Zhantao Yang, Handz Handz, Yulan Guo, Shuai Shao, Qinglin Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add condition-level curriculum (ablation) | OmniCamera · Trajectory-controlled T2V | TransErr: 3.512 -> 2.064 | Improved |
| add condition-level curriculum (ablation) | OmniCamera · Trajectory-controlled T2V | FVD: 1024.31 -> 893.95 | Improved |
| add condition-level curriculum (ablation) | OmniCamera · Reference-video-controlled T2V | TransErr: 9.510 -> 7.109 | Improved |
| add condition-level curriculum (ablation) | OmniCamera · Trajectory-controlled V2V | TransErr: 7.425 -> 5.933 | Improved |
| add data-level curriculum (ablation) | OmniCamera · Trajectory-controlled T2V | TransErr: 2.845 -> 2.064 | Improved |
| add data-level curriculum (ablation) | OmniCamera · Trajectory-controlled T2V | FVD: 965.84 -> 893.95 | Improved |
| add data-level curriculum (ablation) | OmniCamera · Reference-video-controlled T2V | TransErr: 8.324 -> 7.109 | Improved |
| add UE5 synthetic data (ablation) | OmniCamera · Trajectory-controlled T2V | TransErr: 3.105 -> 2.064 | Improved |
| add UE5 synthetic data (ablation) | OmniCamera · Reference-video-controlled T2V | TransErr: 8.845 -> 7.109 | Improved |
| add real-world data (ablation) | OmniCamera · Trajectory-controlled T2V | FVD: 1150.45 -> 893.95 | Improved |
| add real-world data (ablation) | OmniCamera · Reference-video-controlled T2V | FVD: 1085.24 -> 868.63 | Improved |
| add real-world data (ablation) | OmniCamera · Trajectory-controlled T2V | TransErr: 2.152 -> 2.064 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Generative Omnimatte: Learning to Decompose Video into Layers (CVPR 2025 · similarity 0.88)
- CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation (AAAI 2025 · similarity 0.88)
- UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics (CVPR 2025 · similarity 0.87)
- CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation (NeurIPS 2026 · similarity 0.87)
- DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation (CVPR 2025 · similarity 0.86)
- ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
