Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function

TL;DR

This paper introduces a fast, learning-based method for detailed 3D facial reconstruction from multi-view images, utilizing an implicit function to improve accuracy over existing approaches.

Contribution

It proposes a novel implicit function approach for regressing matching costs, enhancing detailed facial geometry recovery compared to prior learning-based methods.

Findings

Outperforms state-of-the-art learning-based MVS in accuracy

Achieves detailed 3D face reconstruction within dozens of seconds

Effectively recovers detailed facial shapes using implicit functions

Abstract

Recovering detailed facial geometry from a set of calibrated multi-view images is valuable for its wide range of applications. Traditional multi-view stereo (MVS) methods adopt an optimization-based scheme to regularize the matching cost. Recently, learning-based methods integrate all these into an end-to-end neural network and show superiority of efficiency. In this paper, we propose a novel architecture to recover extremely detailed 3D faces within dozens of seconds. Unlike previous learning-based methods that regularize the cost volume via 3D CNN, we propose to learn an implicit function for regressing the matching cost. By fitting a 3D morphable model from multi-view images, the features of multiple images are extracted and aggregated in the mesh-attached UV space, which makes the implicit function more effective in recovering detailed facial shape. Our method outperforms SOTA learning-based MVS in accuracy by a large margin on the FaceScape dataset. The code and data are released in https://github.com/zhuhao-nju/mvfr.