AI Paper Atlas

Research map / Video / Video generation

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

Li Hu, Guangyuan Wang, Zhen Shen, Xin Gao, Dechao Meng, Lian Zhuo, Peng Zhang, Bang Zhang, Liefeng Bo

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 66 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add spatial blending of object guider features (ablation)Animate Anyone 2 · Own dataset (ablation)FVD: 191.23 -> 186.17Improved
Add spatial blending of object guider features (ablation)Animate Anyone 2 · Own dataset (ablation)SSIM: 0.789 -> 0.794Improved
Add depth-wise pose modulation (ablation)Animate Anyone 2 · Own dataset (ablation)FVD: 211.15 -> 186.17Improved
Add depth-wise pose modulation (ablation)Animate Anyone 2 · Own dataset (ablation)SSIM: 0.769 -> 0.794Improved
Use shape-agnostic mask instead of precise character mask or bounding box (ablation)Animate Anyone 2 · qualitative ablationvisual qualityImproved
Use the full environment-aware model instead of compositing animation onto inpainted backgroundAnimate Anyone 2 · Own dataset (character-environment affordance)FVD: 195.45 -> 186.17Improved
Add extra video pretraining before fine-tuning on TikTokAnimate Anyone 2 · TikTok benchmarkFVD: 158.97 -> 144.65Improved
Add extra video pretraining before fine-tuning on TikTokAnimate Anyone 2 · TikTok benchmarkSSIM: 0.778 -> 0.812Improved
Use Animate Anyone 2 instead of Animate Anyone (TikTok only)Animate Anyone · TikTok benchmarkFVD: 171.90 -> 158.97Improved
Use Animate Anyone 2 instead of Champ on own datasetChamp · Own dataset (100 videos)FVD: 205.79 -> 172.54Improved
Use Animate Anyone 2 without extra pretraining instead of Champ* with itChamp* · TikTok benchmarkSSIM: 0.802 -> 0.778Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy