Recover Canonical-View Faces in the Wild with Deep Neural Networks

TL;DR

This paper introduces a deep learning framework that recovers canonical-view face images from wild conditions, reducing intra-personal variations and improving face verification performance without relying on 3D data or manual labeling.

Contribution

It proposes a novel deep neural network approach that learns to transform diverse face images into canonical views automatically, enhancing face recognition robustness.

Findings

Achieves state-of-the-art results on LFW dataset.

Effectively reduces intra-personal variations in face images.

Automatically synthesizes canonical views without manual labeling.

Abstract

Face images in the wild undergo large intra-personal variations, such as poses, illuminations, occlusions, and low resolutions, which cause great challenges to face-related applications. This paper addresses this challenge by proposing a new deep learning framework that can recover the canonical view of face images. It dramatically reduces the intra-person variances, while maintaining the inter-person discriminativeness. Unlike the existing face reconstruction methods that were either evaluated in controlled 2D environment or employed 3D information, our approach directly learns the transformation from the face images with a complex set of variations to their canonical views. At the training stage, to avoid the costly process of labeling canonical-view images from the training set by hand, we have devised a new measurement to automatically select or synthesize a canonical-view image for each identity. As an application, this face recovery approach is used for face verification. Facial features are learned from the recovered canonical-view face images by using a facial component-based convolutional neural network. Our approach achieves the state-of-the-art performance on the LFW dataset.