"Sparse + Low-Rank'' Tensor Completion Approach for Recovering Images and Videos
This addresses a fundamental challenge in face recognition and computer vision, offering incremental improvements for domain-specific applications.
The paper tackles the problem of recovering color images and videos from highly undersampled data by proposing a novel tensor completion approach that explores sparsity under the discrete cosine transform, demonstrating better performance than existing state-of-the-art methods, especially with high missing data ratios.
Recovering color images and videos from highly undersampled data is a fundamental and challenging task in face recognition and computer vision. By the multi-dimensional nature of color images and videos, in this paper, we propose a novel tensor completion approach, which is able to efficiently explore the sparsity of tensor data under the discrete cosine transform (DCT). Specifically, we introduce two ``sparse + low-rank'' tensor completion models as well as two implementable algorithms for finding their solutions. The first one is a DCT-based sparse plus weighted nuclear norm induced low-rank minimization model. The second one is a DCT-based sparse plus $p$-shrinking mapping induced low-rank optimization model. Moreover, we accordingly propose two implementable augmented Lagrangian-based algorithms for solving the underlying optimization models. A series of numerical experiments including color image inpainting and video data recovery demonstrate that our proposed approach performs better than many existing state-of-the-art tensor completion methods, especially for the case when the ratio of missing data is high.