mlsanityData to 14 Oct 2026

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

arXiv 2301.10208 ↗First posted 24 Jan 2023cs.CV eess.IVcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction. SAUNet customizes a Residual Adaptive ADMM Framework (R2ADMM) to connect each stage of the network via a group of learnable parameters to promote the usage of mask prior, which greatly stabilizes training and solves the accuracy degradation issue. Additionally, we introduce a simple convolutional modulation block (CMB), which leads to efficient training, easy scale-up, and less computation. Coupling these two designs, SAUNet can be scaled to non-trivial 13 stages with continuous improvement. Without bells and whistles, SAUNet improves both performance and speed compared with the previous state-of-the-art counterparts, which makes it feasible for practical high-resolution HSI reconstruction scenarios. We set new records on CAVE and KAIST HSI reconstruction benchmarks. Code and models are available at https://github.com/hustvl/SAUNet.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 46 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

22 of 46 references.

References · 22

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  6. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  7. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  8. 2022How Do Vision Transformers Work?cited by 307
  9. 2022Focal Modulation Networkscited by 186
  10. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  11. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  12. 2018Rank Minimization for Snapshot Compressive Imagingcited by 99
10 more
  1. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  2. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  3. 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
  4. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  5. 2021Deep Gaussian Scale Mixture Prior for Spectral Compressive Imagingcited by 58
  6. 2020GAP-net for Snapshot Compressive Imagingcited by 54
  7. 2017Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysiscited by 12
  8. 2016Adaptive ADMM with Spectral Penalty Parameter Selectioncited by 10
  9. 2017Proximal Alternating Direction Network: A Globally Converged Deep Unrolling Frameworkcited by 3
  10. 2017Adaptive Relaxed ADMM: Convergence Theory and Practical Implementationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imagingcited by 1
  2. 2023BSS-Bench: Towards Reproducible and Effective Band Selection Searchcited by 0