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

20 Mar 2019  ·  Yu Deng, Jiaolong Yang, Sicheng Xu, Dong Chen, Yunde Jia, Xin Tong ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Face Reconstruction NoW Benchmark Deep3DFaceRecon PyTorch Mean Reconstruction Error (mm) 1.41±1.21 # 2
Stdev Reconstruction Error (mm) 1.21 # 2
Median Reconstruction Error 1.11 # 2
3D Face Reconstruction NoW Benchmark Deng et al. 2019 Mean Reconstruction Error (mm) 1.54±1.29 # 6
Stdev Reconstruction Error (mm) 1.29 # 4
Median Reconstruction Error 1.23 # 6

Methods


No methods listed for this paper. Add relevant methods here