Learning from Millions of 3D Scans for Large-scale 3D Face Recognition

TL;DR

This paper introduces a large-scale 3D face recognition system trained on over 3 million scans, significantly advancing accuracy and robustness in open world scenarios compared to previous methods.

Contribution

It presents the first deep CNN for 3D face recognition trained on a massive dataset and a protocol for merging existing datasets for large-scale testing.

Findings

Outperforms state-of-the-art by over 10% without fine-tuning.

Uses 3.1 million 3D scans of 100K identities for training.

Demonstrates effectiveness in open world face recognition.

Abstract

Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face recognition problem.