mlsanityData to 14 Oct 2026

WaveFace: Authentic Face Restoration with Efficient Frequency Recovery

arXiv 2403.12760 ↗First posted 19 Mar 2024cs.CVcited by 20

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details. In this work, we propose WaveFace to solve the problems in the frequency domain, where low- and high-frequency components decomposed by wavelet transformation are considered individually to maximize authenticity as well as efficiency. The diffusion model is applied to recover the low-frequency component only, which presents general information of the original image but 1/16 in size. To preserve the original identity, the generation is conditioned on the low-frequency component of low-quality images at each denoising step. Meanwhile, high-frequency components at multiple decomposition levels are handled by a unified network, which recovers complex facial details in a single step. Evaluations on four benchmark datasets show that: 1) WaveFace outperforms state-of-the-art methods in authenticity, especially in terms of identity preservation, and 2) authentic images are restored with the efficiency 10x faster than existing diffusion model-based BFR methods.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 34 of its 42 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

34 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec
  2. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  3. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  11. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
19 more
  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  2. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 449
  3. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  4. 2015WIDER FACE: A Face Detection Benchmarkcited by 298
  5. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  6. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  7. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  8. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 144
  9. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 117
  10. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  11. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  12. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94
  13. 2018Learning Warped Guidance for Blind Face Restorationcited by 87
  14. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  15. 2018Deep Semantic Face Deblurringcited by 80
  16. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  17. 2022Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsingcited by 26
  18. 2022Deep Face Restoration: A Surveycited by 17
  19. 2021EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Datasetcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 6.

20 papers.

Sort:

By area:

  1. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  2. 2026The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Resultscited by 13
  3. 2025NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Resultscited by 10
  4. 2025InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restorationcited by 9
  5. 2025Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restorationcited by 8
  6. 2024AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Priorcited by 4
  7. 2025IQPFR: An Image Quality Prior for Blind Face Restoration and Beyondcited by 3
  8. 2026Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restorationcited by 3
  9. 2024LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolutioncited by 2
  10. 2025DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidancecited by 2
  11. 2025Unlocking the Potential of Diffusion Priors in Blind Face Restorationcited by 2
  12. 2025HonestFace: Towards Honest Face Restoration with One-Step Diffusion Modelcited by 1
8 more
  1. 2025Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolutioncited by 1
  2. 2025Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidancecited by 0
  3. 2025QuantFace: Efficient Quantization for Face Restorationcited by 0
  4. 2025Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascadecited by 0
  5. 2026TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoisingcited by 0
  6. 2026SFKD: Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interactioncited by 0
  7. 2026WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restorationcited by 0
  8. 2026Domain-adaptive Zero-Shot Image Enhancement via Locality-Constrained Diffusion Guidancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond
  2. 2025FaceMe: Robust Blind Face Restoration with Personal Identification
  3. 2023DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration
  4. 2025TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration
  5. 2024Towards Unsupervised Blind Face Restoration using Diffusion Prior
  6. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Prior
  7. 20243D Priors-Guided Diffusion for Blind Face Restoration
  8. 2024ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration