MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion

TL;DR

This paper introduces MARLow, a novel image completion method that combines multiplanar autoregressive modeling with low-rank minimization to effectively exploit nonlocal self-similarity and cross-dimensional correlations, outperforming existing methods.

Contribution

The paper presents a joint multiplanar AR and low-rank approach for image completion, effectively leveraging cross-dimensional correlations and nonlocal self-similarity, with extensions to multichannel images.

Findings

Significantly outperforms state-of-the-art methods

Effective even with 90% pixel missing rate

Extensible to multichannel images

Abstract

In this paper, we propose a novel multiplanar autoregressive (AR) model to exploit the correlation in cross-dimensional planes of a similar patch group collected in an image, which has long been neglected by previous AR models. On that basis, we then present a joint multiplanar AR and low-rank based approach (MARLow) for image completion from random sampling, which exploits the nonlocal self-similarity within natural images more effectively. Specifically, the multiplanar AR model constraints the local stationarity in different cross-sections of the patch group, while the low-rank minimization captures the intrinsic coherence of nonlocal patches. The proposed approach can be readily extended to multichannel images (e.g. color images), by simultaneously considering the correlation in different channels. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art methods, even if the pixel missing rate is as high as 90%.