Research map / Video / Video generation
MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation
Xirui Hu, Yanbo Ding, Jiahao Wang, Tingting Shi, Yali Wang, Guo Zhi Zhi, Weizhan Zhang
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 motion normalization pipeline (MNP) (ablation) | MotionWeaver · DualDynamics | FVD: 198.5 -> 145.7 | Improved |
| add group attention module (GAM) (ablation) | MotionWeaver · DualDynamics | FVD: 183.2 -> 145.7 | Improved |
| add depth-aware attention (DAA) with occlusion supervision (ablation) | MotionWeaver · DualDynamics | FVD: 167.1 -> 145.7 | Improved |
| add dynamic C-RoPE (DCR) (ablation) | MotionWeaver · DualDynamics | FVD: 225.6 -> 145.7 | Improved |
| add hierarchical-4D supervision (H4S) instead of fixed MSE+occlusion loss (ablation) | MotionWeaver · DualDynamics | FVD: 174.3 -> 145.7 | Improved |
| add dynamic C-RoPE (DCR) (ablation) | MotionWeaver · DualDynamics | CLIP: 0.8270 -> 0.9041 | Improved |
| add motion normalization pipeline (MNP) (ablation) | MotionWeaver · DualDynamics | PSNR: 26.34 -> 29.19 | Improved |
| add group attention module (GAM) (ablation) | MotionWeaver · DualDynamics | FID-VID: 25.76 -> 20.34 | Improved |
| add H4S supervision (ablation) | MotionWeaver · DualDynamics | PSNR: 29.04 -> 29.19 | No clear effect |
| add H4S supervision (ablation) | MotionWeaver · DualDynamics | L1: 0.5011 -> 0.4836 | Improved |
Closest papers by meaning
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.88)
- Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025 · similarity 0.87)
- EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation (NeurIPS 2025 · similarity 0.87)
- Universal Humanoid Motion Representations for Physics-Based Control (ICLR 2024 · similarity 0.87)
- Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling (ICLR 2025 · similarity 0.86)
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (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.
