Self-supervised Learning of Detailed 3D Face Reconstruction

TL;DR

This paper introduces a self-supervised framework for detailed 3D face reconstruction from a single image, eliminating the need for ground-truth 3D models by using the input image as supervision.

Contribution

It proposes a novel end-to-end learning approach that combines a coarse 3DMM model with a UV-space displacement map, enabling detailed face reconstruction without supervised 3D data.

Findings

Outperforms previous methods in detailed face reconstruction

Effective use of UV-space for learning facial details

No need for surrogate ground-truth 3D models

Abstract

In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-toimage translation network to predict a displacement map in UVspace. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of the proposed method over previous work.