A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation
This is an incremental improvement for video processing tasks, enhancing separation accuracy in a specific domain.
The paper tackled video foreground-background separation by proposing a deep-unfolded network that models temporal correlations between frames, outperforming a state-of-the-art RPCA network on the moving MNIST dataset.
Deep unfolded neural networks are designed by unrolling the iterations of optimization algorithms. They can be shown to achieve faster convergence and higher accuracy than their optimization counterparts. This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) with application to video foreground-background separation. Unlike existing designs, our approach focuses on modeling the temporal correlation between the sparse representations of consecutive video frames. To this end, we perform the unfolding of an iterative algorithm for solving reweighted $\ell_1$-$\ell_1$ minimization; this unfolding leads to a different proximal operator (a.k.a. different activation function) adaptively learned per neuron. Experimentation using the moving MNIST dataset shows that the proposed network outperforms a recently proposed state-of-the-art RPCA network in the task of video foreground-background separation.