no code implementations • 11 May 2022 • Peter Vouras, Kumar Vijay Mishra, Alexandra Artusio-Glimpse, Samuel Pinilla, Angeliki Xenaki, David W. Griffith, Karen Egiazarian
Rapid developments in synthetic aperture (SA) systems, which generate a larger aperture with greater angular resolution than is inherently possible from the physical dimensions of a single sensor alone, are leading to novel research avenues in several signal processing applications.
no code implementations • 14 Apr 2022 • Wenzhu Xing, Karen Egiazarian
One of the recent methods of image restoration based on a Swin Transformer (ST), SwinIR, demonstrates state-of-the-art performance with a smaller number of parameters than neural network-based methods.
no code implementations • 3 Mar 2022 • Samuel Pinilla, Kumar Vijay Mishra, Igor Shevkunov, Mojtaba Soltanalian, Vladimir Katkovnik, Karen Egiazarian
Phase retrieval in optical imaging refers to the recovery of a complex signal from phaseless data acquired in the form of its diffraction patterns.
no code implementations • 24 Sep 2021 • Sheyda Ghanbaralizadeh Bahnemiri, Mykola Ponomarenko, Karen Egiazarian
Comparison with the ideal case, when denoising is applied using ground-truth sigma-map, shows that a difference of corresponding PSNR values for most of noise levels is within 0. 1-0. 2 dB and does not exceeds 0. 6 dB.
1 code implementation • CVPR 2021 • Wenzhu Xing, Karen Egiazarian
A problem of finding a joint solution of the multiple image restoration tasks just begun to attract an increased attention of researchers.
no code implementations • 14 May 2021 • Vladimir Katkovnik, Igor Shevkunov, Karen Egiazarian
A novel formulation of the hyperspectral broadband phase retrieval is developed for the scenario where both object and modulation phase masks are spectrally varying.
no code implementations • 9 Mar 2021 • Seyyed Reza Miri Rostami, Samuel Pinilla, Igor Shevkunov, Vladimir Katkovnik, Karen Egiazarian
The simulation results also reveal that optimizing the optical power-balance, Fresnel order, and the number of levels parameters are essential for system performance attaining an improvement of up to 5dB of PSNR using the optimized OTF compared with its counterpart lensless setup.
Optics Image and Video Processing
1 code implementation • 2 Mar 2020 • Pham Huu Thanh Binh, Cristóvão Cruz, Karen Egiazarian
This paper proposes a learning-based denoising method called FlashLight CNN (FLCNN) that implements a deep neural network for image denoising.
no code implementations • 22 Oct 2019 • Junqi Tang, Karen Egiazarian, Mohammad Golbabaee, Mike Davies
We investigate this phenomenon and propose a theory-inspired mechanism for the practitioners to efficiently characterize whether it is beneficial for an inverse problem to be solved by stochastic optimization techniques or not.
no code implementations • 4 Oct 2019 • Vladimir Katkovnik, Igor Shevkunov, Karen Egiazarian
Broadband hyperspectral digital holography and Fourier transform spectroscopy are important instruments in various science and application fields.
1 code implementation • 6 Mar 2018 • Cristóvão Cruz, Alessandro Foi, Vladimir Katkovnik, Karen Egiazarian
We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising.
no code implementations • 29 Nov 2017 • Mykola Ponomarenko, Nikolay Gapon, Viacheslav Voronin, Karen Egiazarian
In the paper, a new method of blind estimation of noise variance in a single highly textured image is proposed.
no code implementations • 2 Nov 2017 • Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiem
After carrying out a perceptual quality assessment of distorted images, the mean opinion scores (MOS) are obtained and compared with the values of known full reference quality metrics.
no code implementations • 1 Nov 2017 • Vladimir Katkovnik, Mykola Ponomarenko, Karen Egiazarian
Phase imaging and wavefront reconstruction from noisy observations of complex exponent is a topic of this paper.
no code implementations • 13 Apr 2017 • Cristóvão Cruz, Rakesh Mehta, Vladimir Katkovnik, Karen Egiazarian
In this paper we propose a self-similarity based approach that is able to use large groups of similar patches extracted from the input image to solve the SISR problem.
no code implementations • 4 Sep 2006 • Alessandro Foi, Vladimir Katkovnik, Karen Egiazarian
The use of this shape-adaptive transform for denoising and deblurring has been recently proposed, showing a remarkable performance.