W-Net: A Facial Feature-Guided Face Super-Resolution Network
Not on the map. Why?
Abstract (arXiv)
Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low reconstruction efficiency and insufficient utilization of prior information. Considering that faces are highly structured objects, effectively leveraging facial priors to improve FSR results is a worthwhile endeavor. This paper proposes a novel network architecture called W-Net to address this challenge. W-Net leverages meticulously designed Parsing Block to fully exploit the resolution potential of LR image. We use this parsing map as an attention prior, effectively integrating information from both the parsing map and LR images. Simultaneously, we perform multiple fusions in various dimensions through the W-shaped network structure combined with the LPF(LR-Parsing Map Fusion Module). Additionally, we utilize a facial parsing graph as a mask, assigning different weights and loss functions to key facial areas to balance the performance of our reconstructed facial images between perceptual quality and pixel accuracy. We conducted extensive comparative experiments, not only limited to conventional facial super-resolution metrics but also extending to downstream tasks such as facial recognition and facial keypoint detection. The experiments demonstrate that W-Net exhibits outstanding performance in quantitative metrics, visual quality, and downstream tasks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 2 Jun 2024.
Builds on
37 of 61 references.
References · 37
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
- 2015Spatial Transformer Networkscited by 1,429
25 more
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
- 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
- 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
- 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
- 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
- 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
- 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
- 2021Transformer for Single Image Super-Resolutioncited by 150
- 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
- 2020HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishmentcited by 70
- 2020Learning Spatial Attention for Face Super-Resolutioncited by 55
- 2020Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimationcited by 53
- 2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40
- 2018Super-Identity Convolutional Neural Network for Face Hallucinationcited by 39
- 2017Attention-Aware Face Hallucination via Deep Reinforcement Learningcited by 33
- 2020Face Hallucination via Split-Attention in Split-Attention Networkcited by 24
- 2022CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolutioncited by 19
- 2017Learning to Hallucinate Face Images via Component Generation and Enhancementcited by 11
- 2020MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Networkcited by 9
- 2021Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognitioncited by 6
- 2021TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Networkcited by 2
- 2021AGA-GAN: Attribute Guided Attention Generative Adversarial Network with U-Net for Face Hallucinationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.