Research map / Video / Video generation
AniClipart: Clipart Animation with Text-to-Video Priors
Ronghuan Wu, Wanchao Su, Kede Ma, Jing Liao
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 ARAP shape deformation instead of linear blend skinning (ablation) | AniClipart · Clipart animation (30 clipart) | Geometric deviation (lower better): 60.56 -> 50.98 | Improved |
| add ARAP shape deformation instead of linear blend skinning (ablation) | AniClipart · Clipart animation (30 clipart) | Motion vibrancy: 17.13 -> 20.87 | Improved |
| add Bezier trajectory parameterization instead of direct per-frame keypoint prediction (ablation) | AniClipart · Clipart animation (30 clipart) | Temporal consistency (lower better): 13.9341 -> 8.5115 | Improved |
| add Bezier trajectory parameterization instead of direct per-frame keypoint prediction (ablation) | AniClipart · Clipart animation (30 clipart) | Motion vibrancy: 102.66 -> 20.87 | Hurt |
| use cubic instead of first-order Bezier trajectories (ablation) | AniClipart · Clipart animation (30 clipart) | Temporal consistency (lower better): 4.7950 -> 8.5115 | Hurt |
| use cubic instead of first-order Bezier trajectories (ablation) | AniClipart · Clipart animation (30 clipart) | Motion vibrancy: 8.96 -> 20.87 | Improved |
| use video SDS loss instead of X-CLIP loss (ablation) | AniClipart · Clipart animation (30 clipart) | Geometric deviation (lower better): 108.81 -> 50.98 | Improved |
| use video SDS loss instead of image SDS loss (ablation) | AniClipart · Clipart animation (30 clipart) | Motion vibrancy: 7.57 -> 20.87 | Improved |
| add skeleton fidelity loss (ablation) | AniClipart · Clipart animation (30 clipart) | Geometric deviation (lower better): 265.92 -> 50.98 | Improved |
| add skeleton fidelity loss (ablation) | AniClipart · Clipart animation (30 clipart) | Temporal consistency (lower better): 8.3768 -> 8.5115 | No clear effect |
| use AniClipart instead of Gal23 sketch animation baseline | AniClipart · Clipart animation (30 clipart) | CLIP score: 0.8379 -> 0.9414 | Improved |
| use AniClipart instead of ToonCrafter (strongest identity baseline) | AniClipart · Clipart animation (30 clipart) | CLIP score: 0.9292 -> 0.9414 | Improved |
Later papers that compared with this method
1 later accepted paper reports AniClipart as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- FlexiClip: Locality-Preserving Free-Form Character Animation (ICML 2025 · better on 9 of 10 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- VideoCrafter2 — VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models (CVPR 2024) · better on 2 of 2 shared results
- DynamiCrafter — DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors (ECCV 2024) · 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
- FlexiClip: Locality-Preserving Free-Form Character Animation (ICML 2025 · similarity 0.93)
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · similarity 0.88)
- Breathing Life Into Sketches Using Text-to-Video Priors (CVPR 2024 · similarity 0.87)
- AniDoc: Animation Creation Made Easier (CVPR 2025 · similarity 0.86)
- Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025 · similarity 0.86)
- Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model (CVPR 2024 · 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.
