ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild

TL;DR

ReLoo is a novel method that reconstructs high-quality 3D models of humans in loose garments from monocular videos by decomposing the human into layered neural representations and modeling free clothing deformations.

Contribution

ReLoo introduces a layered neural human representation and a flexible virtual bone deformation module to handle loose clothing in monocular 3D human reconstruction.

Findings

ReLoo outperforms prior methods on indoor and in-the-wild datasets.

It effectively reconstructs non-rigid clothing deformations.

The method achieves high-quality 3D models from monocular videos.

Abstract

While previous years have seen great progress in the 3D reconstruction of humans from monocular videos, few of the state-of-the-art methods are able to handle loose garments that exhibit large non-rigid surface deformations during articulation. This limits the application of such methods to humans that are dressed in standard pants or T-shirts. Our method, ReLoo, overcomes this limitation and reconstructs high-quality 3D models of humans dressed in loose garments from monocular in-the-wild videos. To tackle this problem, we first establish a layered neural human representation that decomposes clothed humans into a neural inner body and outer clothing. On top of the layered neural representation, we further introduce a non-hierarchical virtual bone deformation module for the clothing layer that can freely move, which allows the accurate recovery of non-rigidly deforming loose clothing. A global optimization jointly optimizes the shape, appearance, and deformations of the human body and clothing via multi-layer differentiable volume rendering. To evaluate ReLoo, we record subjects with dynamically deforming garments in a multi-view capture studio. This evaluation, both on existing and our novel dataset, demonstrates ReLoo's clear superiority over prior art on both indoor datasets and in-the-wild videos.