1 code implementation • 2 Jun 2023 • Nikola Janjušević, Amirhossein Khalilian-Gourtani, Adeen Flinker, Yao Wang
Nonlocal self-similarity within natural images has become an increasingly popular prior in deep-learning models.
Ranked #5 on Grayscale Image Denoising on BSD68 sigma50
1 code implementation • 23 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.
1 code implementation • 2 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.
1 code implementation • 5 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.
Ranked #9 on Grayscale Image Denoising on BSD68 sigma25
no code implementations • 1 Jan 2021 • Nikola Pavle Janjusevic, Amirhossein Khalilian-Gourtani, Yao Wang
Sparse representation via a learned dictionary is a powerful prior for natural images.
no code implementations • 17 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.