mlsanityData to 7 Oct 2026

Focal Frequency Loss for Image Reconstruction and Synthesis

arXiv 2012.12821 ↗First posted 23 Dec 2020cs.CV cs.LG eess.IVcited by 204

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, offering great impedance against the loss of important frequency information due to the inherent bias of neural networks. We demonstrate the versatility and effectiveness of focal frequency loss to improve popular models, such as VAE, pix2pix, and SPADE, in both perceptual quality and quantitative performance. We further show its potential on StyleGAN2.

Key facts. Cited by 204 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 21; 2023: 44; 2024: 47; 2025: 41; 2026: 48.

204 papers.

Sort:

By area:

  1. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  2. 2022Diffusion Probabilistic Model Made Slimcited by 121
  3. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  4. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 116
  5. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 70
  6. 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
  7. 2023FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Informationcited by 64
  8. 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
  9. 2024Bidirectional Multi-Scale Implicit Neural Representations for Image Derainingcited by 54
  10. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  11. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
  12. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
38 more
  1. 2023CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understandingcited by 48
  2. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  3. 2024RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusioncited by 41
  4. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  5. 2022The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Trainingcited by 33
  6. 2022Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNcited by 31
  7. 2023Explicitly Minimizing the Blur Error of Variational Autoencoderscited by 29
  8. 2023Frequency Domain-based Dataset Distillationcited by 28
  9. 2023FreeKD: Knowledge Distillation via Semantic Frequency Promptcited by 27
  10. 2023SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolutioncited by 27
  11. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  12. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  13. 2025The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencodingcited by 21
  14. 2022Y-Net: A Spatiospectral Dual-Encoder Networkfor Medical Image Segmentationcited by 19
  15. 2024Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Surveycited by 19
  16. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  17. 2023Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencodercited by 18
  18. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18
  19. 2024Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restorationcited by 18
  20. 2023OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolutioncited by 17
  21. 20243D-GSW: 3D Gaussian Splatting for Robust Watermarkingcited by 17
  22. 2024Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifactscited by 16
  23. 2024Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcastingcited by 16
  24. 2022GLaMa: Joint Spatial and Frequency Loss for General Image Inpaintingcited by 15
  25. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 14
  26. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  27. 2023Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approachcited by 13
  28. 2022Shadow-Aware Dynamic Convolution for Shadow Removalcited by 11
  29. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  30. 2024Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolutioncited by 11
  31. 2024Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularizationcited by 11
  32. 2026Representation Alignment for Just Image Transformers is not Easier than You Thinkcited by 11
  33. 2023FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentationcited by 10
  34. 2024Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolutioncited by 10
  35. 2024DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformercited by 10
  36. 2023Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generationcited by 9
  37. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  38. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9

50 most cited of 204 All 204 (JSON)