FastHuman: Reconstructing High-Quality Clothed Human in Minutes

TL;DR

FastHuman is a rapid method for reconstructing detailed clothed human body shapes from multi-view images, combining mesh-based techniques and sphere harmonics to achieve high quality in minutes.

Contribution

The paper introduces a mesh-based patch warping and SH illumination approach that significantly accelerates high-quality clothed human reconstruction compared to implicit methods.

Findings

Achieves high-quality reconstructions in minutes

Reduces optimization and rendering times substantially

Effective on both synthetic and real-world datasets

Abstract

We propose an approach for optimizing high-quality clothed human body shapes in minutes, using multi-view posed images. While traditional neural rendering methods struggle to disentangle geometry and appearance using only rendering loss, and are computationally intensive, our method uses a mesh-based patch warping technique to ensure multi-view photometric consistency, and sphere harmonics (SH) illumination to refine geometric details efficiently. We employ oriented point clouds' shape representation and SH shading, which significantly reduces optimization and rendering times compared to implicit methods. Our approach has demonstrated promising results on both synthetic and real-world datasets, making it an effective solution for rapidly generating high-quality human body shapes. Project page \href{https://l1346792580123.github.io/nccsfs/}{https://l1346792580123.github.io/nccsfs/}