mlsanityData to 7 Oct 2026

Arbitrary-Scale Image Synthesis

arXiv 2204.02273 ↗First posted 5 Apr 2022cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good perceptual quality at the scales for which the model is not trained explicitly. We propose the design of scale-consistent positional encodings invariant to our generator's layers transformations. This enables the generation of arbitrary-scale images even at scales unseen during training. Moreover, we incorporate novel inter-scale augmentations into our pipeline and partial generation training to facilitate the synthesis of consistent images at arbitrary scales. Lastly, we show competitive results for a continuum of scales on various commonly used datasets for image synthesis.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

40 of 48 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  11. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  12. 2016Generative Adversarial Text to Image Synthesiscited by 735
28 more
  1. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  2. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  3. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  4. 2018Which Training Methods for GANs do actually Converge?cited by 672
  5. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  6. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  7. 2019On the "steerability" of generative adversarial networkscited by 247
  8. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  9. 2020Adversarial Generation of Continuous Imagescited by 135
  10. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  11. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  12. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  13. 2020StyleGAN2 Distillation for Feed-forward Image Manipulationcited by 78
  14. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  15. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  16. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  17. 2020Efficient Semantic Image Synthesis via Class-Adaptive Normalizationcited by 58
  18. 2021In&Out : Diverse Image Outpainting via GAN Inversioncited by 55
  19. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  20. 2020SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objectscited by 43
  21. 2018Learning Hierarchical Semantic Image Manipulation through Structured Representationscited by 27
  22. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 24
  23. 2018SMIT: Stochastic Multi-Label Image-to-Image Translationcited by 21
  24. 2021Toward Spatially Unbiased Generative Modelscited by 17
  25. 2021Efficient Conditional GAN Transfer with Knowledge Propagation across Classescited by 13
  26. 2019SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameterscited by 10
  27. 2021DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editingcited by 7
  28. 2020LocoGAN -- Locally Convolutional GANcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 5; 2025: 3.

20 papers.

Sort:

By area:

  1. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  2. 2025PixNerd: Pixel Neural Field Diffusioncited by 75
  3. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  4. 2022A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentialscited by 45
  5. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  6. 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decodercited by 25
  7. 2022Pyramidal Denoising Diffusion Probabilistic Modelscited by 22
  8. 2023Polynomial Implicit Neural Representations For Large Diverse Datasetscited by 18
  9. 2024Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networkscited by 18
  10. 2024DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representationscited by 16
  11. 2024Image Neural Field Diffusion Modelscited by 13
  12. 2023Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Modelscited by 11
8 more
  1. 2023UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generationcited by 9
  2. 2022FunkNN: Neural Interpolation for Functional Generationcited by 4
  3. 2022Unveiling The Mask of Position-Information Pattern Through the Mist of Image Featurescited by 3
  4. 2023StyleGenes: Discrete and Efficient Latent Distributions for GANscited by 2
  5. 2025MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary Resolutionscited by 1
  6. 2025Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolutioncited by 1
  7. 2023Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesiscited by 0
  8. 2023Disentangled Contrastive Image Translation for Nighttime Surveillancecited by 0