Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling

TL;DR

Ani3DHuman introduces a novel framework that combines kinematic models with video diffusion priors, employing self-guided stochastic sampling to produce photorealistic 3D human animations with detailed non-rigid motion.

Contribution

The paper presents a layered motion representation and a self-guided stochastic sampling method to improve photorealism and identity preservation in 3D human animation.

Findings

Outperforms existing methods in photorealism and quality.

Effectively restores non-rigid motion in 3D human animation.

Demonstrates robustness of the stochastic sampling approach.

Abstract

Current 3D human animation methods struggle to achieve photorealism: kinematics-based approaches lack non-rigid dynamics (e.g., clothing dynamics), while methods that leverage video diffusion priors can synthesize non-rigid motion but suffer from quality artifacts and identity loss. To overcome these limitations, we present Ani3DHuman, a framework that marries kinematics-based animation with video diffusion priors. We first introduce a layered motion representation that disentangles rigid motion from residual non-rigid motion. Rigid motion is generated by a kinematic method, which then produces a coarse rendering to guide the video diffusion model in generating video sequences that restore the residual non-rigid motion. However, this restoration task, based on diffusion sampling, is highly challenging, as the initial renderings are out-of-distribution, causing standard deterministic ODE samplers to fail. Therefore, we propose a novel self-guided stochastic sampling method, which effectively addresses the out-of-distribution problem by combining stochastic sampling (for photorealistic quality) with self-guidance (for identity fidelity). These restored videos provide high-quality supervision, enabling the optimization of the residual non-rigid motion field. Extensive experiments demonstrate that \MethodName can generate photorealistic 3D human animation, outperforming existing methods. Code is available in https://github.com/qiisun/ani3dhuman.