A Deep-Unfolded Spatiotemporal RPCA Network For L+S Decomposition

TL;DR

This paper introduces DUST-RPCA, a deep unfolded spatiotemporal network that enhances low-rank and sparse decomposition for background modeling, achieving better accuracy and convergence than existing methods.

Contribution

It proposes a novel deep unfolded spatiotemporal RPCA network that leverages spatial and temporal continuity for improved low-rank and sparse decomposition.

Findings

DUST-RPCA outperforms existing deep unfolded RPCA networks in accuracy.

The method converges faster than traditional RPCA algorithms.

Experimental results on moving MNIST validate the effectiveness of the approach.

Abstract

Low-rank and sparse decomposition based methods find their use in many applications involving background modeling such as clutter suppression and object tracking. While Robust Principal Component Analysis (RPCA) has achieved great success in performing this task, it can take hundreds of iterations to converge and its performance decreases in the presence of different phenomena such as occlusion, jitter and fast motion. The recently proposed deep unfolded networks, on the other hand, have demonstrated better accuracy and improved convergence over both their iterative equivalents as well as over other neural network architectures. In this work, we propose a novel deep unfolded spatiotemporal RPCA (DUST-RPCA) network, which explicitly takes advantage of the spatial and temporal continuity in the low-rank component. Our experimental results on the moving MNIST dataset indicate that DUST-RPCA gives better accuracy when compared with the existing state of the art deep unfolded RPCA networks.