Research map / 3D vision / Face and shape
DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses
Yatian Pang, Bin Zhu, Bin Lin, Mingzhe Zheng, Francis E. H. Tay, Ser-Nam Lim, Harry Yang, Li Yuan
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 pose guidance (ablation) | DreamDance · TikTok | FVD: 175.37 -> 153.07 | Improved |
| add depth guidance (ablation) | DreamDance · TikTok | FVD: 193.23 -> 153.07 | Improved |
| add normal guidance (ablation) | DreamDance · TikTok | FVD: 183.84 -> 153.07 | Improved |
| add depth guidance (ablation) | DreamDance · TikTok | SSIM: 0.701 -> 0.798 | Improved |
| add geometry attention in cross-domain controller (ablation) | DreamDance · TikTok | FVD: 165.27 -> 153.07 | Improved |
| add geometry attention in cross-domain controller (ablation) | DreamDance · TikTok | SSIM: 0.767 -> 0.798 | Improved |
| add geometry attention in cross-domain controller (ablation) | DreamDance · TikTok | FID-VID: 21.93 -> 19.86 | Improved |
| add multi-domain CFG in geometry stage (ablation) | Mutually Aligned Geometry Diffusion Model · generated normal maps (qualitative) | visual quality | Improved |
| add geometry attention in geometry stage (ablation) | Mutually Aligned Geometry Diffusion Model · generated depth/normal maps (qualitative) | mutual alignment | Improved |
| use generated normal and depth in place of SMPL renderings | DreamDance vs Champ · TikTok | FVD: 170.20 -> 153.07 | Improved |
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.
- Champ — Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance (ECCV 2024) · better on 6 of 6 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
- DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance (ICCV 2025 · similarity 0.90)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.88)
- DisPose: Disentangling Pose Guidance for Controllable Human Image Animation (ICLR 2025 · similarity 0.88)
- Free-viewpoint Human Animation with Pose-correlated Reference Selection (CVPR 2025 · similarity 0.87)
- MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model (CVPR 2024 · similarity 0.86)
- VideoMDM: Towards 3D Human Motion Generation From 2D Supervision (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.
