Research map / Video / Video generation
MotionFollower: Editing Video Motion via Score-Guided Diffusion
Shuyuan Tu, Qi Dai, Zihao Zhang, Sicheng Xie, Zhi-Qi Cheng, Chong Luo, Xintong Han, Zuxuan Wu, Yu-Gang 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 ReCtr appearance controller (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 545.39 -> 276.04 | Improved |
| use ReCtr (convolution) instead of MagicAnimate RNet (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 288.57 -> 276.04 | Improved |
| use PoCtr instead of ControlNet (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 381.52 -> 276.04 | Improved |
| use PoCtr instead of ControlNet (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | Mem: 15.2G -> 9.8G | Improved |
| add score guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 437.69 -> 276.04 | Improved |
| add S_fg guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 372.34 -> 276.04 | Improved |
| add S_over guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 312.24 -> 276.04 | Improved |
| add S_body guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 285.17 -> 276.04 | Improved |
| add S_com guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 280.28 -> 276.04 | Improved |
| use all masks in score guidance (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FVD: 442.34 -> 276.04 | Improved |
| add M_e and M_r masks in Eq.2 (ablation) | MotionFollower · 100 in-the-wild videos (ablation) | FID-VID: 23.71 -> 12.42 | Improved |
| use MotionFollower over MotionEditor | MotionEditor · 100 in-the-wild videos | FVD: 395.43 -> 276.04 | Improved |
Later papers that compared with this method
1 later accepted paper reports MotionFollower as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Collaboratively “Copy & Paste” 2D-3D Features for Complex Video-to-Video Motion Editing (AAAI 2026 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- AnimateAnyone — Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024) · better on 4 of 4 shared results
- MagicAnimate — MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model (CVPR 2024) · better on 4 of 4 shared results
- MotionEditor — MotionEditor: Editing Video Motion via Content-Aware Diffusion (CVPR 2024) · better on 3 of 3 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
- MotionEditor: Editing Video Motion via Content-Aware Diffusion (CVPR 2024 · similarity 0.90)
- FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025 · similarity 0.89)
- Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators (ICLR 2024 · similarity 0.89)
- VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models (CVPR 2024 · similarity 0.87)
- Dynamic Motion Blending for Versatile Motion Editing (CVPR 2025 · similarity 0.87)
- Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model (AAAI 2024 · 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.
