mlsanityData to 7 Oct 2026

Image Generators with Conditionally-Independent Pixel Synthesis

arXiv 2011.13775 ↗First posted 27 Nov 2020cs.CV cs.AI cs.LGcited by 105

Not on the map. Why?

Abstract (arXiv)

Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. Here, we present a new architecture for image generators, where the color value at each pixel is computed independently given the value of a random latent vector and the coordinate of that pixel. No spatial convolutions or similar operations that propagate information across pixels are involved during the synthesis. We analyze the modeling capabilities of such generators when trained in an adversarial fashion, and observe the new generators to achieve similar generation quality to state-of-the-art convolutional generators. We also investigate several interesting properties unique to the new architecture.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 33; 2023: 26; 2024: 15; 2025: 6; 2026: 1.

105 papers.

Sort:

By area:

  1. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  4. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  5. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  6. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  7. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  8. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  9. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  10. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  11. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  12. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
38 more
  1. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  2. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  3. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  4. 2021Generative Models as Distributions of Functionscited by 89
  5. 2022COIN++: Neural Compression Across Modalitiescited by 81
  6. 2023Score-based Diffusion Models in Function Spacecited by 80
  7. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  8. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  9. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  10. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  11. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  12. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  13. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  14. 2021On the Frequency Bias of Generative Modelscited by 60
  15. 2021Improved Transformer for High-Resolution GANscited by 59
  16. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  17. 2021CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fieldscited by 55
  18. 2023Renderable Neural Radiance Map for Visual Navigationcited by 51
  19. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  20. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  21. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  22. 2022UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translationcited by 42
  23. 2023Task-Oriented Human-Object Interactions Generation with Implicit Neural Representationscited by 41
  24. 2023Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictionscited by 38
  25. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  26. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  27. 2021SphereSR: 360deg Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representationcited by 33
  28. 2022TileGen: Tileable, Controllable Material Generation and Capturecited by 27
  29. 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decodercited by 25
  30. 2021Dynamic Inference with Neural Interpreterscited by 24
  31. 2022HyperTime: Implicit Neural Representation for Time Seriescited by 24
  32. 2022Pyramidal Denoising Diffusion Probabilistic Modelscited by 22
  33. 2023Variational Autoencoding Neural Operatorscited by 22
  34. 2023∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified Statescited by 21
  35. 2021Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesiscited by 20
  36. 2022Arbitrary-Scale Image Synthesiscited by 20
  37. 2022Improving GANs with A Dynamic Discriminatorcited by 20
  38. 2023Dense Pixel-to-Pixel Harmonization via Continuous Image Representationcited by 19

50 most cited of 105 All 105 (JSON)