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

Junyu Wang, Shijie Wang, Ruijie Zhang, Zengqiang Zheng, Wenyu Liu +1 more
5/16/2023
cs.CVeess.IV

Official code: hustvl/RND-SCI (11 stars, MIT, last commit 2023-05-18).

Abstract

We present RND-SCI, a novel framework for compressive hyperspectral image (HSI) reconstruction. Our framework decomposes the reconstructed object into range-space and null-space components, where the range-space part ensures the solution conforms to the compression process, and the null-space term introduces a deep HSI prior to constraining the output to have satisfactory properties. RND-SCI is not only simple in design with strong interpretability but also can be easily adapted to various HSI reconstruction networks, improving the quality of HSIs with minimal computational overhead. RND-SCI significantly boosts the performance of HSI reconstruction networks in retraining, fine-tuning or plugging into a pre-trained off-the-shelf model. Based on the framework and SAUNet, we design an extremely fast HSI reconstruction network, RND-SAUNet, which achieves an astounding 91 frames per second while maintaining superior reconstruction accuracy compared to other less time-consuming methods. Code and models are available at https://github.com/hustvl/RND-SCI.

View on arXivView PDF

Code Implementations(1)

hustvl/RND-SCIOfficial100%
MIT

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

110C++, CudaMay 16, 20233 years agoMIT
hyperspectral-imaginglow-level-vision

Similar Papers

In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging

87% match1 repo152023

Cross-Scan Mamba with Masked Training for Robust Spectral Imaging

87% match2024

Binarized Spectral Compressive Imaging

86% match2 repos1.1k2023

Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising

85% match2022

Physics-Informed Untrained Learning for RGB-Guided Superresolution Single-Pixel Hyperspectral Imaging

84% match2026

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

84% match1 repo322023

Cite this paper

@article{wang2023rangenull,
  title  = {A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imaging},
  author = {Junyu Wang and Shijie Wang and Ruijie Zhang and Zengqiang Zheng and Wenyu Liu and Xinggang Wang},
  year   = {2023},
  eprint = {2305.09746},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.09746v1}
}

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/2305.09746.svg)](https://codeofpaper.com/paper/2305.09746)

Discussion