mlsanityData to 7 Oct 2026

Spectral Distribution Aware Image Generation

arXiv 2012.03110 ↗First posted 5 Dec 2020cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Recent advances in deep generative models for photo-realistic images have led to high quality visual results. Such models learn to generate data from a given training distribution such that generated images can not be easily distinguished from real images by the human eye. Yet, recent work on the detection of such fake images pointed out that they are actually easily distinguishable by artifacts in their frequency spectra. In this paper, we propose to generate images according to the frequency distribution of the real data by employing a spectral discriminator. The proposed discriminator is lightweight, modular and works stably with different commonly used GAN losses. We show that the resulting models can better generate images with realistic frequency spectra, which are thus harder to detect by this cue.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 4; 2023: 7; 2024: 4; 2025: 4; 2026: 2.

29 papers.

Sort:

By area:

  1. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  2. 2021On the Frequency Bias of Generative Modelscited by 60
  3. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  4. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  5. 2021SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domaincited by 30
  6. 2022FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfittingcited by 28
  7. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  8. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  9. 2022GLaMa: Joint Spatial and Frequency Loss for General Image Inpaintingcited by 15
  10. 2022Misleading Deep-Fake Detection with GAN Fingerprintscited by 11
  11. 2024When Semantic Segmentation Meets Frequency Aliasingcited by 10
  12. 2024Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpaintingcited by 9
17 more
  1. 2023As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domaincited by 8
  2. 2023On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvementcited by 8
  3. 2023Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Contextcited by 8
  4. 2022Simpler is better: spectral regularization and up-sampling techniques for variational autoencoderscited by 6
  5. 2024Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restorationcited by 6
  6. 2023Towards Robust GAN-generated Image Detection: a Multi-view Completion Representationcited by 5
  7. 2024Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profilecited by 4
  8. 2023Guided Frequency Loss for Image Restorationcited by 3
  9. 2025Spatial Frequency Modulation for Semantic Segmentationcited by 3
  10. 2021FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defectscited by 1
  11. 2021DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learningcited by 1
  12. 2025Zero-Shot Visual Deepfake Detection: Can AI Predict and Prevent Fake Content Before It's Created?cited by 1
  13. 2025Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detectioncited by 1
  14. 2026Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Imagescited by 1
  15. 2021Investigating Shifts in GAN Output-Distributionscited by 0
  16. 2023Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Poolingcited by 0
  17. 2026Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weightingcited by 0