Data to 14 Oct 2026

Progressive Face Super-Resolution via Attention to Facial Landmark

arXiv 1908.08239 ↗First posted 22 Aug 2019cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 19; 2023: 11; 2024: 15; 2025: 11; 2026: 6.

73 papers.

Sort:

By area:

2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40
2022GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priorscited by 39
2023RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairscited by 33
2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
2021Deep Learning-based Face Super-Resolution: A Surveycited by 32
2023Dual Associated Encoder for Face Restorationcited by 23

38 more

2023Towards Real-World Blind Face Restoration with Generative Diffusion Priorcited by 22
2022CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolutioncited by 19
2022GLEAN: Generative Latent Bank for Image Super-Resolution and Beyondcited by 19
2023Survey on Deep Face Restoration: From Non-blind to Blind and Beyondcited by 18
2022Deep Face Restoration: A Surveycited by 17
2022From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolutioncited by 15
2021Multi-modality Deep Restoration of Extremely Compressed Face Videoscited by 14
2024InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attentioncited by 13
2026The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Resultscited by 13
2021EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Datasetcited by 12
2021Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolutioncited by 10
2022Blind Face Restoration: Benchmark Datasets and a Baseline Modelcited by 10
2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Modelscited by 10
2024F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restorationcited by 10
2025NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Resultscited by 10
2024Towards Real-world Video Face Restoration: A New Benchmarkcited by 6
2023Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformercited by 5
2024CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Modelscited by 5
2025DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learningcited by 5
2022FaceFormer: Scale-aware Blind Face Restoration with Transformerscited by 4
2024ARoFace: Alignment Robustness to Improve Low-Quality Face Recognitioncited by 4
2024AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Priorcited by 4
2022Priors in Deep Image Restoration and Enhancement: A Surveycited by 3
2022Multi-Prior Learning via Neural Architecture Search for Blind Face Restorationcited by 3
2023Super-Resolving Face Image by Facial Parsing Informationcited by 3
2023Personalized Restoration via Dual-Pivot Tuningcited by 3
2025IQPFR: An Image Quality Prior for Blind Face Restoration and Beyondcited by 3
2025Robust ID-Specific Face Restoration via Alignment Learningcited by 3
2022HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplarscited by 2
2022Deep Semantic Statistics Matching (D2SM) Denoising Networkcited by 2
2022Face Super-Resolution with Progressive Embedding of Multi-scale Face Priorscited by 2
2024W-Net: A Facial Feature-Guided Face Super-Resolution Networkcited by 2
2024Towards Unsupervised Blind Face Restoration using Diffusion Priorcited by 2
2024Analysis and Benchmarking of Extending Blind Face Image Restoration to Videoscited by 2
2021Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraintcited by 1
2021SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Networkcited by 1
2022Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priorscited by 1
2022Super-resolution Reconstruction of Single Image for Latent featurescited by 1

50 most cited of 73 All 73 (JSON)