mlsanityData to 7 Oct 2026

InfinityGAN: Towards Infinite-Pixel Image Synthesis

arXiv 2104.03963 ↗First posted 8 Apr 2021cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

We present a novel framework, InfinityGAN, for arbitrary-sized image generation. The task is associated with several key challenges. First, scaling existing models to an arbitrarily large image size is resource-constrained, in terms of both computation and availability of large-field-of-view training data. InfinityGAN trains and infers in a seamless patch-by-patch manner with low computational resources. Second, large images should be locally and globally consistent, avoid repetitive patterns, and look realistic. To address these, InfinityGAN disentangles global appearances, local structures, and textures. With this formulation, we can generate images with spatial size and level of details not attainable before. Experimental evaluation validates that InfinityGAN generates images with superior realism compared to baselines and features parallelizable inference. Finally, we show several applications unlocked by our approach, such as spatial style fusion, multi-modal outpainting, and image inbetweening. All applications can be operated with arbitrary input and output sizes. Please find the full version of the paper at https://openreview.net/forum?id=ufGMqIM0a4b .

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

41 of 53 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  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. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2017Improved Training of Wasserstein GANscited by 2,223
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
29 more
  1. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  2. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  3. 2016Pixel Recurrent Neural Networkscited by 814
  4. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  5. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  8. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  9. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  10. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  11. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  12. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  13. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  14. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  15. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  16. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  17. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  18. 2020Improved Techniques for Training Single-Image GANscited by 77
  19. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  20. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  21. 2019Boundless: Generative Adversarial Networks for Image Extensioncited by 62
  22. 2021In&Out : Diverse Image Outpainting via GAN Inversioncited by 55
  23. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  24. 2019Very Long Natural Scenery Image Prediction by Outpaintingcited by 50
  25. 2017TextureGAN: Controlling Deep Image Synthesis with Texture Patchescited by 47
  26. 2020Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Spacecited by 34
  27. 2018Painting Outside the Box: Image Outpainting with GANscited by 30
  28. 2021Bridging the Visual Gap: Wide-Range Image Blendingcited by 12
  29. 2018Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 19; 2023: 21; 2024: 11; 2025: 7; 2026: 2.

61 papers.

Sort:

By area:

  1. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  2. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  3. 2022Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encodingcited by 83
  4. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  5. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
  6. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  7. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  8. 2023Single Motion Diffusioncited by 65
  9. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 59
  10. 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Modelcited by 56
  11. 2023Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Modelscited by 48
  12. 2021An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representationcited by 47
38 more
  1. 2023Customizing 360-Degree Panoramas through Text-to-Image Diffusion Modelscited by 47
  2. 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesiscited by 45
  3. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  4. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  5. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  6. 2023CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Queryingcited by 34
  7. 2022Guided Co-Modulated GAN for 360deg Field of View Extrapolationcited by 32
  8. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  9. 2023DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathologycited by 28
  10. 2022Musika! Fast Infinite Waveform Music Generationcited by 24
  11. 2022Text2Light: Zero-Shot Text-Driven HDR Panorama Generationcited by 24
  12. 20233D Cinemagraphy from a Single Imagecited by 23
  13. 2023CityGen: Infinite and Controllable City Layout Generationcited by 22
  14. 2022ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priorscited by 21
  15. 2022Improving GANs with A Dynamic Discriminatorcited by 20
  16. 2023Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistencycited by 19
  17. 2024Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approachcited by 18
  18. 2024PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidancecited by 18
  19. 2023OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolutioncited by 17
  20. 2022Vector Quantized Image-to-Image Translationcited by 16
  21. 2025Compositional Generative Model of Unbounded 4D Citiescited by 16
  22. 2024Urban Scene Diffusion through Semantic Occupancy Mapcited by 14
  23. 2024COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generationcited by 10
  24. 2023Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decorationcited by 9
  25. 2023UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generationcited by 9
  26. 2023LDM3D-VR: Latent Diffusion Model for 3D VRcited by 8
  27. 2024EdgeRelight360: Text-Conditioned 360-Degree HDR Image Generation for Real-Time On-Device Video Portrait Relightingcited by 5
  28. 2024Zero-shot Text-guided Infinite Image Synthesis with LLM guidancecited by 4
  29. 2022Unveiling The Mask of Position-Information Pattern Through the Mist of Image Featurescited by 3
  30. 2022HORIZON: High-Resolution Semantically Controlled Panorama Synthesiscited by 3
  31. 2023Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesiscited by 3
  32. 2024Learning to See Through Dazzlecited by 3
  33. 2024Learning Images Across Scales Using Adversarial Trainingcited by 3
  34. 2022Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systemscited by 2
  35. 2024EarthGen: Generating the World from Top-Down Viewscited by 2
  36. 2022One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPUcited by 1
  37. 2022Scaling Painting Style Transfercited by 1
  38. 2025NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfoldingcited by 1

50 most cited of 61 All 61 (JSON)