AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models

TL;DR

AniCrafter is a novel diffusion-based model that enables realistic, human-centric character animation in open-domain videos with dynamic backgrounds, overcoming limitations of prior structural conditioning methods.

Contribution

The paper introduces an avatar-background conditioning mechanism in diffusion models, enhancing open-domain human animation with dynamic backgrounds and complex poses.

Findings

Outperforms existing methods in open-domain scenarios

Provides stable and versatile animation outputs

Effectively integrates characters into dynamic backgrounds

Abstract

Recent advances in video diffusion models have significantly improved character animation techniques. However, current approaches rely on basic structural conditions such as DWPose or SMPL-X to animate character images, limiting their effectiveness in open-domain scenarios with dynamic backgrounds or challenging human poses. In this paper, we introduce \textbf{AniCrafter}, a diffusion-based human-centric animation model that can seamlessly integrate and animate a given character into open-domain dynamic backgrounds while following given human motion sequences. Built on cutting-edge Image-to-Video (I2V) diffusion architectures, our model incorporates an innovative ''avatar-background'' conditioning mechanism that reframes open-domain human-centric animation as a restoration task, enabling more stable and versatile animation outputs. Experimental results demonstrate the superior performance of our method. Codes are available at https://github.com/MyNiuuu/AniCrafter.