Coarse to Fine Two-Stage Approach to Robust Tensor Completion of Visual Data

TL;DR

This paper introduces a two-stage robust tensor completion method for visual data with significant gross corruption, combining a global coarse completion with local patch refinement and an adaptive outlier mitigation technique.

Contribution

A novel coarse-to-fine framework and an M-estimator-based tensor ring recovery method that effectively handle large-scale outliers in tensor completion.

Findings

Outperforms state-of-the-art robust tensor completion algorithms.

Effectively identifies and mitigates the impact of gross outliers.

Demonstrates superior performance on visual data with heavy corruption.

Abstract

Tensor completion is the problem of estimating the missing values of high-order data from partially observed entries. Data corruption due to prevailing outliers poses major challenges to traditional tensor completion algorithms, which catalyzed the development of robust algorithms that alleviate the effect of outliers. However, existing robust methods largely presume that the corruption is sparse, which may not hold in practice. In this paper, we develop a two-stage robust tensor completion approach to deal with tensor completion of visual data with a large amount of gross corruption. A novel coarse-to-fine framework is proposed which uses a global coarse completion result to guide a local patch refinement process. To efficiently mitigate the effect of a large number of outliers on tensor recovery, we develop a new M-estimator-based robust tensor ring recovery method which can adaptively identify the outliers and alleviate their negative effect in the optimization. The experimental results demonstrate the superior performance of the proposed approach over state-of-the-art robust algorithms for tensor completion.