Research map / Video / Video generation
MoCa: Modeling Object Consistency for 3D Camera Control in Video Generation
Chengzhijing, Xuancheng Zhang, Donglin Di, Chen Wei, Hao Li, Xun Yang
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 Plucker embedding camera representation (ablation) | MoCa · RealEstate10K | TransErr: 0.758 -> 0.703 | Improved |
| add semantic guidance strategy (ablation) | MoCa · RealEstate10K | FID: 243.1 -> 207.4 | Improved |
| add semantic guidance strategy (ablation) | MoCa · VidGen | MS: 95.2% -> 98.3% | Improved |
| add high-frequency object masking (ablation) | MoCa · RealEstate10K | BC: 94.9% -> 96.4% | Improved |
| add high-frequency object masking (ablation) | MoCa · VidGen | OC: 94.3% -> 94.7% | Mixed |
| use cross-attention fusion instead of addition fusion (ablation) | MoCa · RealEstate10K | TransErr: 0.738 -> 0.703 | Improved |
| use cross-attention fusion instead of addition fusion (ablation) | MoCa · RealEstate10K | FVD: 771.8 -> 667.9 | Improved |
| use cross-attention fusion instead of addition fusion (ablation) | MoCa · VidGen | FID: 248.1 -> 232.2 | Improved |
| add Plucker embedding camera representation (ablation) | MoCa · RealEstate10K | OC: 93.5% -> 94.9% | Improved |
| add high-frequency object masking (ablation) | MoCa · VidGen | FVD: 1735.4 -> 1643.7 | Improved |
Closest papers by meaning
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (CVPR 2025 · similarity 0.89)
- VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control (ICLR 2025 · similarity 0.87)
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers (CVPR 2025 · similarity 0.86)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.86)
- 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation (CVPR 2024 · similarity 0.86)
- ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation (CVPR 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.
