Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising

TL;DR

This paper introduces a novel deep equilibrium convolutional sparse coding framework for hyperspectral image denoising, leveraging fixed-point modeling to enhance robustness and detail preservation in noisy HSIs.

Contribution

It proposes a DEQ-based deep equilibrium model that unifies spatial-spectral correlations, nonlocal self-similarities, and global consistency for improved HSI denoising.

Findings

Outperforms state-of-the-art denoising methods in experiments

Effectively preserves image details and spatial-spectral structures

Achieves superior noise reduction and image quality

Abstract

Hyperspectral images (HSIs) play a crucial role in remote sensing but are often degraded by complex noise patterns. Ensuring the physical property of the denoised HSIs is vital for robust HSI denoising, giving the rise of deep unfolding-based methods. However, these methods map the optimization of a physical model to a learnable network with a predefined depth, which lacks convergence guarantees. In contrast, Deep Equilibrium (DEQ) models treat the hidden layers of deep networks as the solution to a fixed-point problem and models them as infinite-depth networks, naturally consistent with the optimization. Under the framework of DEQ, we propose a Deep Equilibrium Convolutional Sparse Coding (DECSC) framework that unifies local spatial-spectral correlations, nonlocal spatial self-similarities, and global spatial consistency for robust HSI denoising. Within the convolutional sparse coding (CSC) framework, we enforce shared 2D convolutional sparse representation to ensure global spatial consistency across bands, while unshared 3D convolutional sparse representation captures local spatial-spectral details. To further exploit nonlocal self-similarities, a transformer block is embedded after the 2D CSC. Additionally, a detail enhancement module is integrated with the 3D CSC to promote image detail preservation. We formulate the proximal gradient descent of the CSC model as a fixed-point problem and transform the iterative updates into a learnable network architecture within the framework of DEQ. Experimental results demonstrate that our DECSC method achieves superior denoising performance compared to state-of-the-art methods.