Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration

TL;DR

This paper introduces a neural architecture search-based framework for blind face restoration that adaptively learns optimal network structures and effectively integrates multiple facial priors for improved image quality.

Contribution

It proposes FRSNet for automatic architecture search and MFPSNet for multi-prior learning, advancing blind face restoration without extensive manual tuning.

Findings

MFPSNet outperforms state-of-the-art methods on synthetic datasets.

MFPSNet achieves superior results on real-world datasets.

The approach effectively combines multiple facial priors for better restoration.

Abstract

Blind Face Restoration (BFR) aims to recover high-quality face images from low-quality ones and usually resorts to facial priors for improving restoration performance. However, current methods still suffer from two major difficulties: 1) how to derive a powerful network architecture without extensive hand tuning; 2) how to capture complementary information from multiple facial priors in one network to improve restoration performance. To this end, we propose a Face Restoration Searching Network (FRSNet) to adaptively search the suitable feature extraction architecture within our specified search space, which can directly contribute to the restoration quality. On the basis of FRSNet, we further design our Multiple Facial Prior Searching Network (MFPSNet) with a multi-prior learning scheme. MFPSNet optimally extracts information from diverse facial priors and fuses the information into image features, ensuring that both external guidance and internal features are reserved. In this way, MFPSNet takes full advantage of semantic-level (parsing maps), geometric-level (facial heatmaps), reference-level (facial dictionaries) and pixel-level (degraded images) information and thus generates faithful and realistic images. Quantitative and qualitative experiments show that MFPSNet performs favorably on both synthetic and real-world datasets against the state-of-the-art BFR methods. The codes are publicly available at: https://github.com/YYJ1anG/MFPSNet.