mlsanityData to 7 Oct 2026

NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results

arXiv 2304.10415 ↗First posted 20 Apr 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet citeLF-InterNet. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR citeDistgLF. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 98 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

40 of 98 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  3. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  4. 2020Pre-Trained Image Processing Transformercited by 891
  5. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  6. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  7. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  8. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  9. 2022VRT: A Video Restoration Transformercited by 219
  10. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  11. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  12. 2021Transformer for Single Image Super-Resolutioncited by 150
28 more
  1. 2021Video Super-Resolution Transformercited by 120
  2. 2022NAFSSR: Stereo Image Super-Resolution Using NAFNetcited by 75
  3. 2022R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesiscited by 69
  4. 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
  5. 2019Learning Parallax Attention for Stereo Image Super-Resolutioncited by 56
  6. 2015Seven ways to improve example-based single image super resolutioncited by 51
  7. 2018EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Imagescited by 46
  8. 2022Disentangling Light Fields for Super-Resolution and Disparity Estimationcited by 42
  9. 2020Deep Video Super-Resolution using HR Optical Flow Estimationcited by 40
  10. 2019Spatial-Angular Interaction for Light Field Image Super-Resolutioncited by 38
  11. 2020Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularizationcited by 36
  12. 2020Symmetric Parallax Attention for Stereo Image Super-Resolutioncited by 35
  13. 2020Deformable 3D Convolution for Video Super-Resolutioncited by 32
  14. 2020NTIRE 2020 Challenge on NonHomogeneous Dehazingcited by 31
  15. 2021Light Field Image Super-Resolution with Transformerscited by 31
  16. 2020Light Field Image Super-Resolution Using Deformable Convolutioncited by 30
  17. 2022Detail-Preserving Transformer for Light Field Image Super-Resolutioncited by 26
  18. 2018A System for Acquiring, Processing, and Rendering Panoramic Light Field Stills for Virtual Realitycited by 24
  19. 2022Occlusion-Aware Cost Constructor for Light Field Depth Estimationcited by 23
  20. 2019High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstructioncited by 22
  21. 2021Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimationcited by 21
  22. 2023Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolutioncited by 21
  23. 2021Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolutioncited by 16
  24. 2021Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Networkcited by 13
  25. 2022Learning Sub-Pixel Disparity Distribution for Light Field Depth Estimationcited by 12
  26. 2022Real-World Light Field Image Super-Resolution via Degradation Modulationcited by 8
  27. 2021Dense Dual-Attention Network for Light Field Image Super-Resolutioncited by 7
  28. 2023PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolutioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 1; 2026: 1.

7 papers.

  1. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  2. 2023Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoisingcited by 6
  3. 2023NTIRE 2023 Quality Assessment of Video Enhancement Challengecited by 6
  4. 2023LFSRDiff: Light Field Image Super-Resolution via Diffusion Modelscited by 5
  5. 2023OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimationcited by 2
  6. 2024MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolutioncited by 1
  7. 2026GTF: Omnidirectional EPI Transformer for Light Field Super-Resolutioncited by 0