Research map / Video / Video generation
MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation
Yanbo Ding, Xirui Hu, Guo Zhi Zhi, Yan Zhang, Xinrui Wang, Zhixiang He, Chi Zhang, Yali Wang, Xuelong Li
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 vector quantization to motion tokens (ablation) | MTVCraft-6B · TikTok | FVD: 332.97 -> 317.21 | Improved |
| use differential (first-frame-relative) joint coordinates (ablation) | MTVCraft-6B · TikTok | FVD: 325.40 -> 317.21 | Improved |
| add z-axis (3D) quantization over 4D (ablation) | MTVCraft-6B · TikTok | FVD: 329.86 -> 317.21 | Improved |
| use 4D RoPE in motion attention instead of no positional encoding (ablation) | MTVCraft-6B · TikTok | FVD: 548.31 -> 317.21 | Improved |
| use 4D RoPE instead of 3D spatial RoPE (ablation) | MTVCraft-6B · TikTok | FVD: 435.80 -> 317.21 | Improved |
| use 4D RoPE instead of learnable PE (ablation) | MTVCraft-6B · TikTok | FVD: 397.64 -> 317.21 | Improved |
| scale backbone from CogVideoX-5B (6B) to Wan-2.1-14B (18B) | MTVCraft · TikTok | FVD: 317.21 -> 276.65 | Improved |
| motion CFG scale 3.0 vs other scales (ablation) | MTVCraft-6B · TikTok | FVD | Improved |
| replace zero-padding with linear/MLP projection for 18B (ablation) | MTVCraft-18B · TikTok | convergence | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MimicMotion — MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025) · better on 2 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
- Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025 · similarity 0.88)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 2025 · similarity 0.87)
- MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling (CVPR 2025 · similarity 0.86)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.86)
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.86)
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · 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.
