Deep Cascaded Bi-Network for Face Hallucination

Abstract

We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landmarks localization or dense correspondence field), we alternatingly optimize two complementary tasks, namely face hallucination and dense correspondence field estimation, in a unified framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details. Extensive experiments demonstrate that such formulation allows exceptional hallucination quality on in-the-wild low-res faces with significant pose and illumination variations.

This paper is to appear in Proceedings of ECCV 2016

References in corpus (4)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Image Super-Resolution Using Deep Convolutional Networks
• WIDER FACE: A Face Detection Benchmark
• Compact Bilinear Pooling

Cited by in corpus (10)

• SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• Attention-Aware Face Hallucination via Deep Reinforcement Learning
• Deep Joint Face Hallucination and Recognition
• Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
• Super-Resolving Face Image by Facial Parsing Information
• Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
• Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
• Accelerating the Super-Resolution Convolutional Neural Network
• To learn image super-resolution, use a GAN to learn how to do image degradation first
• LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network