Topology-Preserved Human Reconstruction with Details

TL;DR

This paper introduces a novel neural network approach that combines implicit surface prediction with explicit mesh modeling to achieve detailed, topology-preserved human reconstruction from single images, overcoming limitations of prior methods.

Contribution

It presents a new end-to-end method that bridges model-based and model-free approaches, preserving topology while capturing fine details.

Findings

Effective on DeepHuman and new dataset

Preserves topology while capturing details

Outperforms existing methods in quality

Abstract

It is challenging to directly estimate the human geometry from a single image due to the high diversity and complexity of body shapes with the various clothing styles. Most of model-based approaches are limited to predict the shape and pose of a minimally clothed body with over-smoothing surface. While capturing the fine detailed geometries, the model-free methods are lack of the fixed mesh topology. To address these issues, we propose a novel topology-preserved human reconstruction approach by bridging the gap between model-based and model-free human reconstruction. We present an end-to-end neural network that simultaneously predicts the pixel-aligned implicit surface and an explicit mesh model built by graph convolutional neural network. Experiments on DeepHuman and our collected dataset showed that our approach is effective. The code will be made publicly available.