Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images

TL;DR

This paper introduces ReEF, a new framework that reconstructs detailed, topology-consistent garment meshes from single images by registering explicit templates to implicit shape fields, improving digital garment modeling.

Contribution

ReEF is the first method to produce separated, topology-consistent garment meshes from single images by combining explicit template registration with implicit shape inference.

Findings

Outperforms existing methods in layered garment reconstruction

Produces high-quality, topology-consistent garment meshes

Enhances digital content creation pipelines

Abstract

Fueled by the power of deep learning techniques and implicit shape learning, recent advances in single-image human digitalization have reached unprecedented accuracy and could recover fine-grained surface details such as garment wrinkles. However, a common problem for the implicit-based methods is that they cannot produce separated and topology-consistent mesh for each garment piece, which is crucial for the current 3D content creation pipeline. To address this issue, we proposed a novel geometry inference framework ReEF that reconstructs topology-consistent layered garment mesh by registering the explicit garment template to the whole-body implicit fields predicted from single images. Experiments demonstrate that our method notably outperforms its counterparts on single-image layered garment reconstruction and could bring high-quality digital assets for further content creation.