LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network

TL;DR

This paper introduces an end-to-end progressive learning framework for face super-resolution that incorporates facial attributes and multi-scale discriminators, significantly improving the quality of hallucinated high-resolution faces from low-resolution images.

Contribution

It proposes a novel attribute-induced, adversarial progressive network that constrains the LR-HR mapping, reducing ambiguity and enhancing super-resolution results.

Findings

Outperforms state-of-the-art methods on CelebA dataset.

Effectively incorporates facial attributes to guide super-resolution.

Achieves high-quality face hallucination at 8x upscaling.

Abstract

Face super-resolution is a challenging and highly ill-posed problem since a low-resolution (LR) face image may correspond to multiple high-resolution (HR) ones during the hallucination process and cause a dramatic identity change for the final super-resolved results. Thus, to address this problem, we propose an end-to-end progressive learning framework incorporating facial attributes and enforcing additional supervision from multi-scale discriminators. By incorporating facial attributes into the learning process and progressively resolving the facial image, the mapping between LR and HR images is constrained more, and this significantly helps to reduce the ambiguity and uncertainty in one-to-many mapping. In addition, we conduct thorough evaluations on the CelebA dataset following the settings of previous works (i.e. super-resolving by a factor of 8x from tiny 16x16 face images.), and the results demonstrate that the proposed approach can yield satisfactory face hallucination images outperforming other state-of-the-art approaches.