Research map / Video / Video generation
LayerAnimate: Layer-level Control for Animation
Yuxue Yang, Lue Fan, Zuzeng Lin, Feng Wang, Zhaoxiang 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 |
|---|---|---|---|
| increase layer capacity from N=1 to N=4 (ablation) | LayerAnimate · I2V | FVD: 87.88 -> 81.36 | Improved |
| increase layer capacity from N=1 to N=2 (ablation) | LayerAnimate · I2V | FVD: 87.88 -> 81.93 | Improved |
| add binary motion state (MA) (ablation) | LayerAnimate · I2V | FVD: 87.96 -> 87.12 | No clear effect |
| add motion scores on top of motion state (ablation) | LayerAnimate · I2V | FVD: 87.12 -> 81.36 | Improved |
| add binary motion state (MA) (ablation) | LayerAnimate · Interpolation | FVD: 59.64 -> 59.79 | No clear effect |
| add motion scores on top of motion state (ablation) | LayerAnimate · Interpolation | FVD: 59.79 -> 53.42 | Improved |
| use heatmap plus offset trajectory representation instead of offset only (ablation) | LayerAnimate · I2V trajectory | FVD: 87.83 -> 72.04 | Improved |
| use heatmap plus offset trajectory representation instead of heatmap only (ablation) | LayerAnimate · I2V trajectory | FVD: 80.57 -> 72.04 | Improved |
| use heatmap plus offset trajectory representation instead of offset only (ablation) | LayerAnimate · I2V trajectory | trajectory MSE: 50.02 -> 46.58 | Improved |
| use heatmap plus offset trajectory representation instead of heatmap only (ablation) | LayerAnimate · I2V trajectory | trajectory MSE: 47.23 -> 46.58 | Improved |
| use LayerAnimate instead of Tora for trajectory control | LayerAnimate · I2V trajectory | trajectory MSE: 352.43 -> 46.58 | Improved |
| use LayerAnimate instead of ToonCrafter for sketch interpolation | LayerAnimate · Interpolation with sketch | FVD: 66.26 -> 15.63 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- SEINE — SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR 2024) · better on 3 of 3 shared results
- Tora — Tora: Trajectory-oriented Diffusion Transformer for Video Generation (CVPR 2025) · better on 2 of 2 shared results
- Framer — Framer: Interactive Frame Interpolation (ICLR 2025) · better on 2 of 2 shared results
- DragAnything — Drag Anything: Motion Control for Anything using Entity Representation (ECCV 2024) · better on 2 of 2 shared results
- AniDoc — AniDoc: Animation Creation Made Easier (CVPR 2025) · better on 1 of 1 shared result
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
- EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration (NeurIPS 2026 · similarity 0.86)
- AniDoc: Animation Creation Made Easier (CVPR 2025 · similarity 0.86)
- MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model (CVPR 2024 · similarity 0.86)
- PhysAnimator: Physics-Guided Generative Cartoon Animation (CVPR 2025 · similarity 0.85)
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · similarity 0.85)
- Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model (CVPR 2024 · similarity 0.84)
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.
