English

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

Computer Vision and Pattern Recognition 2023-01-25 v1 Image and Video Processing

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.

Keywords

Cite

@article{arxiv.2301.10208,
  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},
  journal= {arXiv preprint arXiv:2301.10208},
  year   = {2023}
}

Comments

Project page: https://github.com/hustvl/SAUNet

R2 v1 2026-06-28T08:18:57.256Z