Research map / Video / Video generation
Video Motion Graphs
Haiyang Liu, Zhan Xu, Fa-Ting Hong, Hsin-Ping Huang, Yi Zhou, Yang Zhou
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 MDM motion guidance (ablation) | HMInterp (s = 1) · VFI ablation | FVD: 1.391 -> 1.210 | Improved |
| use MDM guidance instead of linear guidance (ablation) | HMInterp (s = 1) · VFI ablation | FVD: 1.297 -> 1.210 | Improved |
| add reference decoder (ablation) | HMInterp (s = 1) · VFI ablation | PSNR: 37.21 -> 39.53 | Improved |
| use duplicated frames instead of zero padding in reference decoder (ablation) | HMInterp (s = 1) · VFI ablation | PSNR: 38.13 -> 39.53 | Improved |
| add CLIP image encoder (ablation) | HMInterp (s = 1) · VFI ablation | PSNR: 34.07 -> 39.53 | Improved |
| add ReferenceNet (ablation) | HMInterp (s = 1) · VFI ablation | PSNR: 32.68 -> 39.53 | Improved |
| use progressive training (seed image then pose and seed image 8k iters) instead of simultaneous (ablation) | HMInterp · VFI ablation | PSNR: 36.62 -> 37.21 | Improved |
| fine-tune with pose for 8k instead of 30k iterations (ablation) | HMInterp · VFI ablation | PSNR: 36.87 -> 37.21 | Improved |
| increase reference database size from 10s to 1000s (ablation) | Video Motion Graphs · Reference database length | FVD: 0.611 -> 0.413 | Improved |
| increase masked frames to f = 216 | Video Motion Graphs · Human motion video generation | PSNR: 42.91 -> 39.75 | Hurt |
| use 2 start and end frames more (s = 3 instead of s = 1) | HMInterp · VFI comparison | FVD: 1.210 -> 0.619 | 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.
- 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
- Move-in-2D: 2D-Conditioned Human Motion Generation (CVPR 2025 · similarity 0.87)
- Make Pixels Dance: High-Dynamic Video Generation (CVPR 2024 · similarity 0.87)
- Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think (CVPR 2025 · similarity 0.86)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
- Seamless Human Motion Composition with Blended Positional Encodings (CVPR 2024 · similarity 0.86)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.85)
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.
