mlsanityData to 14 Oct 2026

NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image

arXiv 2005.03412 ↗First posted 7 May 2020eess.IV cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. As in the previous challenge, two tracks were provided: (i) a "Clean" track where HS images are estimated from noise-free RGBs, the RGB images are themselves calculated numerically using the ground-truth HS images and supplied spectral sensitivity functions (ii) a "Real World" track, simulating capture by an uncalibrated and unknown camera, where the HS images are recovered from noisy JPEG-compressed RGB images. A new, larger-than-ever, natural hyperspectral image data set is presented, containing a total of 510 HS images. The Clean and Real World tracks had 103 and 78 registered participants respectively, with 14 teams competing in the final testing phase. A description of the proposed methods, alongside their challenge scores and an extensive evaluation of top performing methods is also provided. They gauge the state-of-the-art in spectral reconstruction from an RGB image.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 5; 2024: 4; 2025: 7; 2026: 1.

30 papers.

Sort:

By area:

  1. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  2. 2023ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolutioncited by 23
  3. 2022Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Reportcited by 11
  4. 2021Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolutioncited by 10
  5. 2021Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Imagescited by 7
  6. 2021Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wildcited by 6
  7. 2022JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imagingcited by 5
  8. 2024Limitations of Data-Driven Spectral Reconstruction -- An Optics-Aware Analysiscited by 5
  9. 2024GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Imagescited by 4
  10. 2021Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representationcited by 3
  11. 2021HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolutioncited by 3
  12. 2021Deep-learning-based Hyperspectral imaging through a RGB cameracited by 2
18 more
  1. 2024Test-time Training for Hyperspectral Image Super-resolutioncited by 2
  2. 2021Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settingscited by 1
  3. 2022D2UF: Deep Coded Aperture Design and Unrolling Algorithm for Compressive Spectral Image Fusioncited by 1
  4. 2022Mixture-Net: Low-Rank Deep Image Prior Inspired by Mixture Models for Spectral Image Recoverycited by 1
  5. 2023mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamicscited by 1
  6. 2023Multispectral Stereo-Image Fusion for 3D Hyperspectral Scene Reconstructioncited by 1
  7. 2024Comparative Analysis of Hyperspectral Image Reconstruction Using Deep Learning for Agricultural and Biological Applicationscited by 1
  8. 2025HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applicationscited by 1
  9. 2026M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstructioncited by 1
  10. 2021Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasetscited by 0
  11. 2023Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependencecited by 0
  12. 2023Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architecturescited by 0
  13. 2025Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Imagescited by 0
  14. 2025NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignmentcited by 0
  15. 2025Model-Guided Network with Cluster-Based Operators for Spatio-Spectral Super-Resolutioncited by 0
  16. 2025Modulate and Reconstruct: Learning Hyperspectral Imaging from Misaligned Smartphone Viewscited by 0
  17. 2025A Deep Unfolding Framework for Diffractive Snapshot Spectral Imagingcited by 0
  18. 2025PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptationcited by 0