Nonlocal Patch-Based Fully-Connected Tensor Network Decomposition for Remote Sensing Image Inpainting

TL;DR

This paper introduces a novel nonlocal patch-based fully-connected tensor network decomposition method for remote sensing image inpainting, leveraging global correlation and self-similarity to achieve state-of-the-art results.

Contribution

It proposes a new NL-FCTN decomposition that stacks similar patches to handle higher-order tensors, with an efficient algorithm and convergence guarantees.

Findings

Achieves state-of-the-art inpainting performance on RSIs.

Effectively leverages nonlocal self-similarity and global correlation.

Demonstrates robustness and efficiency through extensive experiments.

Abstract

Remote sensing image (RSI) inpainting plays an important role in real applications. Recently, fully-connected tensor network (FCTN) decomposition has been shown the remarkable ability to fully characterize the global correlation. Considering the global correlation and the nonlocal self-similarity (NSS) of RSIs, this paper introduces the FCTN decomposition to the whole RSI and its NSS groups, and proposes a novel nonlocal patch-based FCTN (NL-FCTN) decomposition for RSI inpainting. Different from other nonlocal patch-based methods, the NL-FCTN decomposition-based method, which increases tensor order by stacking similar small-sized patches to NSS groups, cleverly leverages the remarkable ability of FCTN decomposition to deal with higher-order tensors. Besides, we propose an efficient proximal alternating minimization-based algorithm to solve the proposed NL-FCTN decomposition-based model with a theoretical convergence guarantee. Extensive experiments on RSIs demonstrate that the proposed method achieves the state-of-the-art inpainting performance in all compared methods.