PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

TL;DR

PSHuman introduces a novel framework for photorealistic 3D human reconstruction from a single image, combining multiview diffusion, cross-scale modeling, and explicit remeshing to produce detailed, consistent, and realistic human meshes.

Contribution

The paper proposes a cross-scale diffusion approach conditioned on SMPL-X priors for improved single-view 3D human reconstruction, addressing geometric distortions and pose inconsistencies.

Findings

Outperforms existing methods in geometry detail and texture fidelity.

Achieves high-quality 3D human meshes with strong generalization.

Demonstrates effectiveness on CAPE and THuman2.1 datasets.

Abstract

Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, full-body reconstruction from a monocular RGB image remains challenging due to the ill-posed nature of the problem and sophisticated clothing topology with self-occlusions. In this paper, we propose PSHuman, a novel framework that explicitly reconstructs human meshes utilizing priors from the multiview diffusion model. It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions, especially on generated faces. To address it, we propose a cross-scale diffusion that models the joint probability distribution of global full-body shape and local facial characteristics, enabling detailed and identity-preserved novel-view generation without any geometric distortion. Moreover, to enhance cross-view body shape consistency of varied human poses, we condition the generative model on parametric models like SMPL-X, which provide body priors and prevent unnatural views inconsistent with human anatomy. Leveraging the generated multi-view normal and color images, we present SMPLX-initialized explicit human carving to recover realistic textured human meshes efficiently. Extensive experimental results and quantitative evaluations on CAPE and THuman2.1 datasets demonstrate PSHumans superiority in geometry details, texture fidelity, and generalization capability.