Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

TL;DR

This paper introduces a fast, accurate 3D face reconstruction method using weakly-supervised learning and multi-image aggregation, achieving state-of-the-art results while handling occlusion and pose variations.

Contribution

It proposes a novel hybrid loss function for weakly-supervised learning and a multi-image shape aggregation technique for improved 3D face reconstruction.

Findings

Outperforms fifteen recent methods on three datasets

Robust to occlusion and large pose variations

Achieves high accuracy and efficiency

Abstract

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information from different images for shape aggregation. Our method is fast, accurate, and robust to occlusion and large pose. We provide comprehensive experiments on three datasets, systematically comparing our method with fifteen recent methods and demonstrating its state-of-the-art performance.