Progressive Face Super-Resolution via Attention to Facial Landmark

Abstract

Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images. The main challenge of face SR is to restore essential facial features without distortion. We propose a novel face SR method that generates photo-realistic 8x super-resolved face images with fully retained facial details. To that end, we adopt a progressive training method, which allows stable training by splitting the network into successive steps, each producing output with a progressively higher resolution. We also propose a novel facial attention loss and apply it at each step to focus on restoring facial attributes in greater details by multiplying the pixel difference and heatmap values. Lastly, we propose a compressed version of the state-of-the-art face alignment network (FAN) for landmark heatmap extraction. With the proposed FAN, we can extract the heatmaps suitable for face SR and also reduce the overall training time. Experimental results verify that our method outperforms state-of-the-art methods in both qualitative and quantitative measurements, especially in perceptual quality.

arXiv commentBMVC 2019 Accepted

Cited by in corpus (18)

• Learning Spatial Attention for Face Super-Resolution
• CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution
• HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
• Edge and Identity Preserving Network for Face Super-Resolution
• SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
• Towards Real-World Blind Face Restoration with Generative Facial Prior
• GAN Prior Embedded Network for Blind Face Restoration in the Wild
• Super-Resolving Face Image by Facial Parsing Information
• Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks
• Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors
• Deep Learning-based Face Super-Resolution: A Survey
• Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos
• PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution
• Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
• Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
• LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network