A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

Junyu Wang, Shijie Wang, Wenyu Liu, Zengqiang Zheng, Xinggang Wang
1/24/2023
cs.CVeess.IV

Official code: hustvl/SAUNet (32 stars, MIT, last commit 2023-02-01).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

hustvl/SAUNetOfficial100%
MIT

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

321MATLAB, PythonJan 20, 20233 years agoMIT
hyperspectral-imaginglow-level-visionunfolding-algorithm

Similar Papers

Adaptive Step-size Perception Unfolding Network with Non-local Hybrid Attention for Hyperspectral Image Reconstruction

87% match2024

Progressive Flow-inspired Unfolding for Spectral Compressive Imaging

86% match2025

A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imaging

84% match1 repo112023

Hierarchical Spatial-Frequency Aggregation for Spectral Deconvolution Imaging

84% match2025

Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging

84% match1 repo212024

Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging

83% match1 repo262025

Cite this paper

@article{wang2023simple,
  title  = {A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction},
  author = {Junyu Wang and Shijie Wang and Wenyu Liu and Zengqiang Zheng and Xinggang Wang},
  year   = {2023},
  eprint = {2301.10208},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.10208v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.10208.svg)](https://codeofpaper.com/paper/2301.10208)

Discussion