Self-supervised Deep Hyperspectral Inpainting with the Plug and Play and Deep Image Prior Models

TL;DR

This paper presents a convergent, stable deep learning algorithm for hyperspectral image inpainting that leverages low-rank and sparse models, outperforming existing methods in quality and reliability.

Contribution

It introduces a novel, guaranteed convergent algorithm, LRS-PnP-DIP(1-Lip), extending low-rank and sparse models for hyperspectral inpainting with proven stability.

Findings

Achieves state-of-the-art inpainting results

Demonstrates superior visual and quantitative performance

Ensures convergence under mild assumptions

Abstract

Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information regarding the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data loss, which can significantly degrade their quality and usefulness. This paper introduces a convergent guaranteed algorithm, LRS-PnP-DIP(1-Lip), which successfully addresses the instability issue of DHP that has been reported before. The proposed algorithm extends the successful joint low-rank and sparse model to further exploit the underlying data structures beyond the conventional and sometimes restrictive unions of subspace models. A stability analysis guarantees the convergence of the proposed algorithm under mild assumptions , which is crucial for its application in real-world scenarios. Extensive experiments demonstrate that the proposed solution consistently delivers visually and quantitatively superior inpainting results, establishing state-of-the-art performance.