Search Results for author: Amirhossein Khalilian-Gourtani

Found 6 papers, 4 papers with code

Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior

1 code implementation23 Apr 2022 Nikola Janjušević, Amirhossein Khalilian-Gourtani, Yao Wang

Gabor-like filters have been observed in the early layers of CNN classifiers and even throughout low-level image processing networks.

Dictionary Learning Image Denoising

CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing

1 code implementation2 Dec 2021 Nikola Janjušević, Amirhossein Khalilian-Gourtani, Yao Wang

In this work, we propose an unrolled convolutional dictionary learning network (CDLNet) and demonstrate its competitive denoising and joint denoising and demosaicing (JDD) performance both in low and high parameter count regimes.

Demosaicking Denoising +1

CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning

1 code implementation5 Mar 2021 Nikola Janjušević, Amirhossein Khalilian-Gourtani, Yao Wang

In addition, we leverage the model's interpretable construction to propose an augmentation of the network's thresholds that enables state-of-the-art blind denoising performance and near-perfect generalization on noise-levels unseen during training.

Dictionary Learning Grayscale Image Denoising +1

Masked-RPCA: Sparse and Low-rank Decomposition Under Overlaying Model and Application to Moving Object Detection

no code implementations17 Sep 2019 Amirhossein Khalilian-Gourtani, Shervin Minaee, Yao Wang

Robust Principal Component Analysis (RPCA) performs low-rank and sparse decomposition and accomplishes such a task when the background is stationary and the foreground is dynamic and relatively small.

Moving Object Detection object-detection

Cannot find the paper you are looking for? You can Submit a new open access paper.