Attention-Aware Face Hallucination via Deep Reinforcement Learning

TL;DR

This paper introduces an attention-aware face hallucination framework using deep reinforcement learning to sequentially select patches for high-quality face image super-resolution, outperforming existing methods especially under challenging conditions.

Contribution

The novel Attention-FH framework employs deep reinforcement learning to adaptively select patches for face super-resolution, capturing global interdependencies and personalizing the enhancement process.

Findings

Outperforms state-of-the-art methods on in-the-wild faces

Effectively handles large pose and illumination variations

Adaptive patch selection improves super-resolution quality

Abstract

Face hallucination is a domain-specific super-resolution problem with the goal to generate high-resolution (HR) faces from low-resolution (LR) input images. In contrast to existing methods that often learn a single patch-to-patch mapping from LR to HR images and are regardless of the contextual interdependency between patches, we propose a novel Attention-aware Face Hallucination (Attention-FH) framework which resorts to deep reinforcement learning for sequentially discovering attended patches and then performing the facial part enhancement by fully exploiting the global interdependency of the image. Specifically, in each time step, the recurrent policy network is proposed to dynamically specify a new attended region by incorporating what happened in the past. The state (i.e., face hallucination result for the whole image) can thus be exploited and updated by the local enhancement network on the selected region. The Attention-FH approach jointly learns the recurrent policy network and local enhancement network through maximizing the long-term reward that reflects the hallucination performance over the whole image. Therefore, our proposed Attention-FH is capable of adaptively personalizing an optimal searching path for each face image according to its own characteristic. Extensive experiments show our approach significantly surpasses the state-of-the-arts on in-the-wild faces with large pose and illumination variations.