mlsanityData to 14 Oct 2026

Learning Continuous Image Representation with Local Implicit Image Function

arXiv 2012.09161 ↗First posted 16 Dec 2020cs.CV cs.LGcited by 552

Not on the map. Why?

Cited by 49 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

How to represent an image? While the visual world is presented in a continuous manner, machines store and see the images in a discrete way with 2D arrays of pixels. In this paper, we seek to learn a continuous representation for images. Inspired by the recent progress in 3D reconstruction with implicit neural representation, we propose Local Implicit Image Function (LIIF), which takes an image coordinate and the 2D deep features around the coordinate as inputs, predicts the RGB value at a given coordinate as an output. Since the coordinates are continuous, LIIF can be presented in arbitrary resolution. To generate the continuous representation for images, we train an encoder with LIIF representation via a self-supervised task with super-resolution. The learned continuous representation can be presented in arbitrary resolution even extrapolate to x30 higher resolution, where the training tasks are not provided. We further show that LIIF representation builds a bridge between discrete and continuous representation in 2D, it naturally supports the learning tasks with size-varied image ground-truths and significantly outperforms the method with resizing the ground-truths.

Key facts. Cited by 552 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 48; 2022: 77; 2023: 113; 2024: 120; 2025: 113; 2026: 81.

552 papers.

Sort:

By area:

  1. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  3. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  4. 2021Neural Fields in Visual Computing and Beyondcited by 540
  5. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  6. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  7. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  8. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  9. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  10. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  11. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 209
  12. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
38 more
  1. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 165
  2. 2021Implicit Neural Representations for Image Compressioncited by 162
  3. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  4. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  5. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  6. 2021Layered Neural Atlases for Consistent Video Editingcited by 137
  7. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  8. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  9. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  10. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 116
  11. 2023CoDeF: Content Deformation Fields for Temporally Consistent Video Processingcited by 108
  12. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  13. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  14. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  15. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 99
  16. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  17. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  18. 2021Generative Models as Distributions of Functionscited by 89
  19. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  20. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  21. 2023Score-based Diffusion Models in Function Spacecited by 82
  22. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  23. 2022E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Contextcited by 76
  24. 2022GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifoldscited by 73
  25. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  26. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representationcited by 71
  27. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  28. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 70
  29. 2022Unified Implicit Neural Stylizationcited by 67
  30. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  31. 2021ACORN: Adaptive Coordinate Networks for Neural Scene Representationcited by 65
  32. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  33. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  34. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  35. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  36. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
  37. 2021On the Frequency Bias of Generative Modelscited by 60
  38. 2022Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fieldscited by 58

50 most cited of 552 All 552 (JSON)