mlsanityData to 7 Oct 2026

Alias-Free Generative Adversarial Networks

arXiv 2106.12423 ↗First posted 23 Jun 2021cs.CV cs.AI cs.LGcited by 1,181

Not on the map. Why?

Cited by 215 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation.

Key facts. Cited by 1,181 papers in the map (data through 7 Oct 2026). Builds on 53 of its 74 references that are in the map. First posted on arXiv 23 Jun 2021.

Builds on

53 of 74 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
38 more
  1. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  2. 2016Group Equivariant Convolutional Networkscited by 1,154
  3. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  4. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  6. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  7. 2018Which Training Methods for GANs do actually Converge?cited by 672
  8. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  9. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  10. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  11. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  12. 2019General E(2)-Equivariant Steerable CNNscited by 441
  13. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  14. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  15. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  16. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  17. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
  18. 2019On the "steerability" of generative adversarial networkscited by 247
  19. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  20. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  21. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  22. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 193
  23. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  24. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 171
  25. 2017Searching for Activation Functionscited by 158
  26. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141
  27. 2020Adversarial Generation of Continuous Imagescited by 135
  28. 2019Deep Scale-spaces: Equivariance Over Scalecited by 113
  29. 2021Paint by Wordcited by 107
  30. 2020Rewriting a Deep Generative Modelcited by 105
  31. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  32. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  33. 2021Only a Matter of Style: Age Transformation Using a Style-Based Regression Modelcited by 92
  34. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  35. 2020Delving Deeper into Anti-aliasing in ConvNetscited by 60
  36. 2020Truly shift-invariant convolutional neural networkscited by 53
  37. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  38. 2018Spatially Controllable Image Synthesis with Internal Representation Collagingcited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 298; 2023: 361; 2024: 236; 2025: 162; 2026: 79.

1,181 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  5. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  6. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  7. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  8. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  9. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  10. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  11. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  12. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
38 more
  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  4. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  5. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  6. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  7. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 396
  8. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  9. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  10. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  11. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  12. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  13. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  14. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  15. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  16. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  17. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  18. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  19. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  20. 2023Self-Consuming Generative Models Go MADcited by 239
  21. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  22. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 225
  23. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  24. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  25. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  26. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  27. 2023Subject-driven Text-to-Image Generation via Apprenticeship Learningcited by 210
  28. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  29. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  30. 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 207
  31. 2023A Survey on Video Diffusion Modelscited by 203
  32. 2023FreeU: Free Lunch in Diffusion U-Netcited by 195
  33. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  34. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  35. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  36. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  37. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  38. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163

50 most cited of 1,181 All 1,181 (JSON)