no code implementations • 7 Dec 2023 • Savva Ignatyev, Daniil Selikhanovych, Oleg Voynov, Yiqun Wang, Peter Wonka, Stamatios Lefkimmiatis, Evgeny Burnaev
We present a novel method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured.
no code implementations • 10 Aug 2023 • Iaroslav Koshelev, Stamatios Lefkimmiatis
In this work we present a novel optimization strategy for image reconstruction tasks under analysis-based image regularization, which promotes sparse and/or low-rank solutions in some learned transform domain.
no code implementations • 20 Apr 2023 • Stamatios Lefkimmiatis, Iaroslav Koshelev
We introduce a novel optimization algorithm for image recovery under learned sparse and low-rank constraints, which we parameterize as weighted extensions of the $\ell_p^p$-vector and $\mathcal S_p^p$ Schatten-matrix quasi-norms for $0\!<p\!\le1$, respectively.
1 code implementation • CVPR 2023 • Kirill Solodskikh, Azim Kurbanov, Ruslan Aydarkhanov, Irina Zhelavskaya, Yury Parfenov, Dehua Song, Stamatios Lefkimmiatis
We call such networks Integral Neural Networks (INNs).
no code implementations • 10 Dec 2021 • Iaroslav Koshelev, Daniil Selikhanovych, Stamatios Lefkimmiatis
In this work, we study the problem of non-blind image deconvolution and propose a novel recurrent network architecture that leads to very competitive restoration results of high image quality.
1 code implementation • ECCV 2020 • Valeriya Pronina, Filippos Kokkinos, Dmitry V. Dylov, Stamatios Lefkimmiatis
Microscopy is a powerful visualization tool in biology, enabling the study of cells, tissues, and the fundamental biological processes; yet, the observed images typically suffer from blur and background noise.
1 code implementation • CVPR 2019 • Filippos Kokkinos, Stamatios Lefkimmiatis
In this work, we focus on the fact that every frame of a burst sequence can be accurately described by a forward (physical) model.
1 code implementation • 16 Jul 2018 • Filippos Kokkinos, Stamatios Lefkimmiatis
Modern approaches try to jointly solve these problems, i. e. joint denoising-demosaicking which is an inherently ill-posed problem given that two-thirds of the intensity information is missing and the rest are perturbed by noise.
1 code implementation • ECCV 2018 • Filippos Kokkinos, Stamatios Lefkimmiatis
Demosaicking and denoising are among the most crucial steps of modern digital camera pipelines and their joint treatment is a highly ill-posed inverse problem where at-least two-thirds of the information are missing and the rest are corrupted by noise.
no code implementations • CVPR 2018 • Stamatios Lefkimmiatis
As opposed to most of the existing deep network approaches, which require the training of a specific model for each considered noise level, the proposed models are able to handle a wide range of noise levels using a single set of learned parameters, while they are very robust when the noise degrading the latent image does not match the statistics of the noise used during training.
no code implementations • CVPR 2017 • Stamatios Lefkimmiatis
We propose a novel deep network architecture for grayscale and color image denoising that is based on a non-local image model.