Research map / Video / Video generation
SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation
Guiyu Zhang, Yabo Chen, Xunzhi Xiang, Junchao Huang, Zhongyu Wang, Li Jiang
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 point-cloud geometric prior c_pcd (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | CamTransErr: 0.46 -> 0.37 | Improved |
| add point-cloud geometric prior c_pcd (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | CamRotErr: 0.07 -> 0.05 | Improved |
| add point-cloud geometric prior c_pcd (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | Box-IoU: 56.74 -> 61.88 | Improved |
| add point-cloud geometric prior c_pcd (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | FVD: 330.64 -> 332.50 | No clear effect |
| add 2D box visual guidance (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | Box-IoU: 54.32 -> 61.88 | Improved |
| add 2D box visual guidance (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | FVD: 337.14 -> 332.50 | Improved |
| add 2D box visual guidance (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | CamTransErr: 0.36 -> 0.37 | No clear effect |
| add 3D trajectory conditioning (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | Box-IoU: 52.16 -> 61.88 | Improved |
| add 3D trajectory conditioning (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | FVD: 343.80 -> 332.50 | Improved |
| add 3D trajectory conditioning (ablation) | SymphoMotion · Custom eval (100 real videos) ablation | CamTransErr: 0.36 -> 0.37 | No clear effect |
| replace MotionCtrl with SymphoMotion for joint control | MotionCtrl · Custom eval (100 real videos) | Box-IoU: 31.42 -> 61.88 | Improved |
| replace Uni3C with SymphoMotion | Uni3C · Custom eval (100 real videos) | FID: 86.66 -> 70.47 | Improved |
Closest papers by meaning
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.89)
- MotionPro: A Precise Motion Controller for Image-to-Video Generation (CVPR 2025 · similarity 0.88)
- DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time (NeurIPS 2026 · similarity 0.88)
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers (CVPR 2025 · similarity 0.88)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 2025 · similarity 0.87)
- FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis (CVPR 2025 · similarity 0.87)
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.
