Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior

TL;DR

This paper introduces S2DIP, an unsupervised hyperspectral image denoising method that combines deep image prior with spatial-spectral constraints, effectively removing mixed noise without requiring training data.

Contribution

The paper proposes S2DIP, integrating spatial-spectral total variation and sparse noise modeling into DIP to improve stability and denoising performance for hyperspectral images.

Findings

S2DIP outperforms state-of-the-art methods in denoising quality.

The method avoids semi-convergence issues of traditional DIP.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Recently, convolutional neural network (CNN)-based methods are proposed for hyperspectral images (HSIs) denoising. Among them, unsupervised methods such as the deep image prior (DIP) have received much attention because these methods do not require any training data. However, DIP suffers from the semi-convergence behavior, i.e., the iteration of DIP needs to terminate by referring to the ground-truth image at the optimal iteration point. In this paper, we propose the spatial-spectral constrained deep image prior (S2DIP) for HSI mixed noise removal. Specifically, we incorporate DIP with a spatial-spectral total variation (SSTV) term to fully preserve the spatial-spectral local smoothness of the HSI and an $\ell_1$-norm term to capture the complex sparse noise. The proposed S2DIP jointly leverages the expressive power brought from the deep CNN without any training data and exploits the HSI and noise structures via hand-crafted priors. Thus, our method avoids the semi-convergence behavior, showing higher stabilities than DIP. Meanwhile, our method largely enhances the HSI denoising ability of DIP. To tackle the proposed denoising model, we develop an alternating direction multiplier method algorithm. Extensive experiments demonstrate that the proposed S2DIP outperforms optimization-based and supervised CNN-based state-of-the-art HSI denoising methods.