Publication Details
Huynh Van Luong, Boris Joukovsky, Boris Joukovsky, Yonina Eldar, Nikos Deligiannis

28th European Signal Processing Conference

Contribution To Book Anthology


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 l1-l1 minimization this unfolding leads to a different proximal operator (aka 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.