CVIVJan 24, 2023

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

arXiv:2301.10208v13 citationsh-index: 73Has Code
Originality Incremental advance
AI Analysis

This is an incremental improvement for practical high-resolution hyperspectral imaging applications.

The paper tackles hyperspectral image reconstruction by proposing SAUNet, a simple unfolding network that improves performance and speed, setting new records on CAIST and KAIST benchmarks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes