mlsanityData to 7 Oct 2026

Aligning Latent and Image Spaces to Connect the Unconnectable

arXiv 2104.06954 ↗First posted 14 Apr 2021cs.CV cs.AIcited by 70

Not on the map. Why?

Abstract (arXiv)

In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spaces. Latent codes, when sampled, are positioned on the coordinate grid, and each pixel is computed from an interpolation of the nearby style codes. We modify the AdaIN mechanism to work in such a setup and train the generator in an adversarial setting to produce images positioned between any two latent vectors. At test time, this allows for generating complex and diverse infinite images and connecting any two unrelated scenes into a single arbitrarily large panorama. Apart from that, we introduce LHQ: a new dataset of lhqsize high-resolution nature landscapes. We test the approach on LHQ, LSUN Tower and LSUN Bridge and outperform the baselines by at least 4 times in terms of quality and diversity of the produced infinite images. The project page is located at https://universome.github.io/alis.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 63 of its 80 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

63 of 80 references.

References · 63

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  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
38 more
  1. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  3. 2018Group Normalizationcited by 1,514
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  6. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2016HyperNetworkscited by 1,003
  10. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  13. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  14. 2018Which Training Methods for GANs do actually Converge?cited by 672
  15. 2017Convolutional Sequence to Sequence Learningcited by 550
  16. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  17. 2017Non-Autoregressive Neural Machine Translationcited by 457
  18. 2018Spherical CNNscited by 452
  19. 2018Assessing Generative Models via Precision and Recallcited by 401
  20. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  21. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  22. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  23. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  24. 2016A Learned Representation For Artistic Stylecited by 340
  25. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  26. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 262
  27. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  28. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  29. 2017Geometric GANcited by 232
  30. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  31. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  32. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  33. 2020Adversarial Latent Autoencoderscited by 155
  34. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  35. 2020Adversarial Generation of Continuous Imagescited by 135
  36. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  37. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  38. 2017The Numerics of GANscited by 104

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 19; 2023: 20; 2024: 11; 2025: 13; 2026: 5.

70 papers.

Sort:

By area:

  1. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  2. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  3. 2025WorldScore: A Unified Evaluation Benchmark for World Generationcited by 143
  4. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  5. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  6. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  7. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
  8. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  9. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  10. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  11. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  12. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
38 more
  1. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  2. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  3. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  4. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
  5. 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesiscited by 45
  6. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  7. 2023Boosting Latent Diffusion with Flow Matchingcited by 44
  8. 2023The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusioncited by 41
  9. 2022Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Modelcited by 39
  10. 2022Sound-Guided Semantic Video Generationcited by 35
  11. 2022Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Modelscited by 27
  12. 2022Musika! Fast Infinite Waveform Music Generationcited by 24
  13. 2022Text2Light: Zero-Shot Text-Driven HDR Panorama Generationcited by 24
  14. 2024Hierarchical Patch Diffusion Models for High-Resolution Video Generationcited by 24
  15. 20253D Scene Generation: A Surveycited by 24
  16. 2026WorldMark: A Unified Benchmark Suite for Interactive Video World Modelscited by 24
  17. 2022Arbitrary-Scale Image Synthesiscited by 20
  18. 2023Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Imagecited by 19
  19. 2022QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelitycited by 18
  20. 2023Polynomial Implicit Neural Representations For Large Diverse Datasetscited by 18
  21. 2022clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPcited by 16
  22. 2023LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesiscited by 15
  23. 2023Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translationcited by 15
  24. 2021StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGANcited by 14
  25. 2024Urban Scene Diffusion through Semantic Occupancy Mapcited by 14
  26. 2023Learning to Evaluate the Artness of AI-generated Imagescited by 10
  27. 2022Robust Sound-Guided Image Manipulationcited by 7
  28. 2025WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Explorationcited by 7
  29. 2022LANIT: Language-Driven Image-to-Image Translation for Unlabeled Datacited by 5
  30. 2025Balanced Image Stylization with Style Matching Scorecited by 5
  31. 2025OuroMamba: A Data-Free Quantization Framework for Vision Mambacited by 5
  32. 2023MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesiscited by 3
  33. 2023Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesiscited by 3
  34. 2024Unveiling the Truth: Exploring Human Gaze Patterns in Fake Imagescited by 3
  35. 2024StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGANcited by 3
  36. 2023Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Maskcited by 2
  37. 2024Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive Mannercited by 2
  38. 2025LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generationcited by 2

50 most cited of 70 All 70 (JSON)