GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images

TL;DR

GMSR-Net is a lightweight, efficient spectral reconstruction model from RGB images that leverages Gradient Mamba blocks with spatial and spectral attention, achieving state-of-the-art accuracy with significantly reduced parameters and computational cost.

Contribution

The paper introduces GMSR-Net, a novel spectral reconstruction model using Gradient Mamba blocks with attention mechanisms, offering superior efficiency and accuracy over existing methods.

Findings

Achieves state-of-the-art spectral reconstruction performance.

Reduces parameters and FLOPS by 10 and 20 times respectively.

Demonstrates a favorable accuracy-efficiency trade-off.

Abstract

Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in handling long-range dependencies, whereas Transformers are constrained by computational efficiency limitations. Recent breakthroughs in state-space model (e.g., Mamba) has attracted significant attention due to its near-linear computational efficiency and superior performance, prompting our investigation into its potential for SR problem. To this end, we propose the Gradient-guided Mamba for Spectral Reconstruction from RGB Images, dubbed GMSR-Net. GMSR-Net is a lightweight model characterized by a global receptive field and linear computational complexity. Its core comprises multiple stacked Gradient Mamba (GM) blocks, each featuring a tri-branch structure. In addition to benefiting from efficient global feature representation by Mamba block, we further innovatively introduce spatial gradient attention and spectral gradient attention to guide the reconstruction of spatial and spectral cues. GMSR-Net demonstrates a significant accuracy-efficiency trade-off, achieving state-of-the-art performance while markedly reducing the number of parameters and computational burdens. Compared to existing approaches, GMSR-Net slashes parameters and FLOPS by substantial margins of 10 times and 20 times, respectively. Code is available at https://github.com/wxy11-27/GMSR.