174 citations · 296 across the 15 of their papers we have counts for
21 papers
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
Baher Mohammad, Ammar Ali, Stamatios Lefkimmiatis
Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on heuristic grouping strategies…
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip +3
Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy ev…
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
Ammar Ali, Baher Mohammad, Denis Makhov +3
We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compr…
Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba
Baher Mohammad, Magauiya Zhussip, Stamatios Lefkimmiatis
We introduce MAVE (Mamba with Cross-Attention for Voice Editing and Synthesis), a novel autoregressive architecture for text-conditioned voice editing and high-fidelity text-to-spe…
CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip +2
Post-training LLM compression often relies on low-rank approximations, which force all columns of a projection matrix to share a single low-dimensional subspace. We propose CoSpaDi…
Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
Magauiya Zhussip, Dmitriy Shopkhoev, Ammar Ali +1
Large language models have revolutionized AI applications, yet their high computational and memory demands hinder their widespread deployment. Existing compression techniques focus…
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip +4
We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance fo…
Robust Two-View Geometry Estimation with Implicit Differentiation
Vladislav Pyatov, Iaroslav Koshelev, Stamatis Lefkimmiatis
We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimat…
GSLoc: Visual Localization with 3D Gaussian Splatting
Kazii Botashev, Vladislav Pyatov, Gonzalo Ferrer +1
We present GSLoc: a new visual localization method that performs dense camera alignment using 3D Gaussian Splatting as a map representation of the scene. GSLoc backpropagates pose…
NeuSD: Surface Completion with Multi-View Text-to-Image Diffusion
Savva Ignatyev, Daniil Selikhanovych, Oleg Voynov +4
We present a novel method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured. Our approach builds on two recent developments…
Iterative Reweighted Least Squares Networks With Convergence Guarantees for Solving Inverse Imaging Problems
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 s…
Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
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 -vector…
DeepRLS: A Recurrent Network Architecture with Least Squares Implicit Layers for Non-blind Image Deconvolution
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 im…
Maxwell Parallel Imaging
Matteo Alessandro Francavilla, Stamatios Lefkimmiatis, Jorge F. Villena +1
Purpose: To develop a general framework for Parallel Imaging (PI) with the use of Maxwell regularization for the estimation of the sensitivity maps (SMs) and constrained optimizati…
Microscopy Image Restoration with Deep Wiener-Kolmogorov filters
Valeriya Pronina, Filippos Kokkinos, Dmitry V. Dylov +1
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 fr…
Iterative Residual CNNs for Burst Photography Applications
Filippos Kokkinos, Stamatios Lefkimmiatis
Modern inexpensive imaging sensors suffer from inherent hardware constraints which often result in captured images of poor quality. Among the most common ways to deal with such lim…
Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
Filippos Kokkinos, Stamatios Lefkimmiatis
Modern digital cameras rely on the sequential execution of separate image processing steps to produce realistic images. The first two steps are usually related to denoising and dem…
Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks
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-th…
Universal Denoising Networks : A Novel CNN Architecture for Image Denoising
Stamatios Lefkimmiatis
We design a novel network architecture for learning discriminative image models that are employed to efficiently tackle the problem of grayscale and color image denoising. Based on…
Non-Local Color Image Denoising with Convolutional Neural Networks
Stamatios Lefkimmiatis
We propose a novel deep network architecture for grayscale and color image denoising that is based on a non-local image model. Our motivation for the overall design of the proposed…
Hessian Schatten-Norm Regularization for Linear Inverse Problems
Stamatios Lefkimmiatis, John Paul Ward, Michael Unser
We introduce a novel family of invariant, convex, and non-quadratic functionals that we employ to derive regularized solutions of ill-posed linear inverse imaging problems. The pro…