WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction

TL;DR

WonderHuman introduces a novel method for reconstructing dynamic 3D human avatars from monocular videos, leveraging generative priors and dual-space optimization to accurately render unseen body parts with high realism.

Contribution

It proposes a dual-space optimization framework using diffusion model priors for high-fidelity unseen part reconstruction from monocular videos.

Findings

Achieves state-of-the-art results in photorealistic rendering of unseen parts.

Effectively reconstructs dynamic human avatars with limited viewpoint data.

Demonstrates robustness and high quality in challenging unseen regions.

Abstract

In this paper, we present WonderHuman to reconstruct dynamic human avatars from a monocular video for high-fidelity novel view synthesis. Previous dynamic human avatar reconstruction methods typically require the input video to have full coverage of the observed human body. However, in daily practice, one typically has access to limited viewpoints, such as monocular front-view videos, making it a cumbersome task for previous methods to reconstruct the unseen parts of the human avatar. To tackle the issue, we present WonderHuman, which leverages 2D generative diffusion model priors to achieve high-quality, photorealistic reconstructions of dynamic human avatars from monocular videos, including accurate rendering of unseen body parts. Our approach introduces a Dual-Space Optimization technique, applying Score Distillation Sampling (SDS) in both canonical and observation spaces to ensure visual consistency and enhance realism in dynamic human reconstruction. Additionally, we present a View Selection strategy and Pose Feature Injection to enforce the consistency between SDS predictions and observed data, ensuring pose-dependent effects and higher fidelity in the reconstructed avatar. In the experiments, our method achieves SOTA performance in producing photorealistic renderings from the given monocular video, particularly for those challenging unseen parts. The project page and source code can be found at https://wyiguanw.github.io/WonderHuman/.