Research map / Video / Video generation
DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency
Xiaojing Zhong, Xinyi Huang, Xiaofeng Yang, Guosheng Lin, Qingyao Wu
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 |
|---|---|---|---|
| extend SDS to normal and image space with reconstruction losses (L_norm, L_rgb) (ablation) | DeCo human generation · text-driven human generation (qualitative) | visual realism of body shape and texture | Improved |
| use only the reconstruction loss in normal and image spaces without SDS guidance (ablation) | DeCo human generation · text-driven human generation (qualitative) | visual quality | Hurt |
| add the lighting-aware video harmonizer (ablation) | DeCo · edited videos (qualitative) | lighting consistency between human and background | Improved |
| decouple human (SMPL-X) from background atlas instead of frame-based or atlas-only editing | DeCo vs baselines · CLIP frame consistency | frame consistency: 96.76 -> 96.91 vs Rerender-A-Video | Improved |
| decouple human (SMPL-X) from background atlas | DeCo vs baselines · CLIP texture faithfulness | texture faithfulness: 32.35 -> 35.25 vs Tune-A-Video | 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.
- Tune-A-Video — Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (ICCV 2023) · better on 3 of 3 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
- ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration (NeurIPS 2026 · similarity 0.88)
- MotionEditor: Editing Video Motion via Content-Aware Diffusion (CVPR 2024 · similarity 0.88)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 2025 · similarity 0.87)
- FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025 · similarity 0.87)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.86)
- Pathways on the Image Manifold: Image Editing via Video Generation (CVPR 2025 · 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.
