Deep Plug-and-Play Prior for Hyperspectral Image Restoration

TL;DR

This paper introduces a versatile deep plug-and-play framework for hyperspectral image restoration that achieves state-of-the-art results across multiple tasks without task-specific retraining.

Contribution

It develops a novel deep HSI denoiser with advanced neural network features and integrates it into a plug-and-play framework for various restoration tasks.

Findings

State-of-the-art denoising performance under Gaussian and complex noise.

Superior results in super-resolution, compressed sensing, and inpainting.

Single model achieves multiple restoration tasks without retraining.

Abstract

Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes. In this paper, we propose to restore HSIs in a unified approach with an effective plug-and-play method, which can jointly retain the flexibility of optimization-based methods and utilize the powerful representation capability of deep neural networks. Specifically, we first develop a new deep HSI denoiser leveraging gated recurrent convolution units, short- and long-term skip connections, and an augmented noise level map to better exploit the abundant spatio-spectral information within HSIs. It, therefore, leads to the state-of-the-art performance on HSI denoising under both Gaussian and complex noise settings. Then, the proposed denoiser is inserted into the plug-and-play framework as a powerful implicit HSI prior to tackle various HSI restoration tasks. Through extensive experiments on HSI super-resolution, compressed sensing, and inpainting, we demonstrate that our approach often achieves superior performance, which is competitive with or even better than the state-of-the-art on each task, via a single model without any task-specific training.