mlsanityData to 7 Oct 2026

HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applications

arXiv 2510.16664 ↗First posted 18 Oct 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Hyperspectral images (HSI) promise to support a range of new applications in computer vision. Recent research has explored the feasibility of generalizable Spectral Reconstruction (SR), the problem of recovering a HSI from a natural three-channel color image in unseen scenarios. However, previous Multi-Scale Attention (MSA) works have only demonstrated sufficient generalizable results for very sparse spectra, while modern HSI sensors contain hundreds of channels. This paper introduces a novel approach to spectral reconstruction via our HYbrid knowledge Distillation and spectral Reconstruction Architecture (HYDRA). Using a Teacher model that encapsulates latent hyperspectral image data and a Student model that learns mappings from natural images to the Teacher's encoded domain, alongside a novel training method, we achieve high-quality spectral reconstruction. This addresses key limitations of prior SR models, providing SOTA performance across all metrics, including an 18% boost in accuracy, and faster inference times than current SOTA models at various channel depths.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

18 of 41 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016Learning without Forgettingcited by 2,465
  5. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  6. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  7. 2020Knowledge Distillation: A Surveycited by 1,578
  8. 2021Multi-Stage Progressive Image Restorationcited by 813
  9. 2013Do Deep Nets Really Need to be Deep?cited by 466
  10. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
  11. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  12. 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
6 more
  1. 2021Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolutioncited by 31
  2. 2020NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Imagecited by 30
  3. 2020Hierarchical Regression Network for Spectral Reconstruction from RGB Imagescited by 29
  4. 2020AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Imagescited by 29
  5. 2023HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methodscited by 26
  6. 2023U-Netmer: U-Net meets Transformer for medical image segmentationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TIDES: Time-Derivative Event Simulation via Deformable Reconstructioncited by 0