11 papers
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
Riccardo Barbano, Alexander Denker, Zeljko Kereta +2
Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pre-trained models remains a…
Learning Binary Sampling Patterns for Single-Pixel Imaging using Bilevel Optimisation
Serban Cristian Tudosie, Alexander Denker, Zeljko Kereta +1
Single-Pixel Imaging (SPI) enables the reconstruction of objects using a single detector through sequential illuminations with structured light patterns. The choice of illumination…
Deep Image Prior for Computed Tomography Reconstruction
Simon Arridge, Riccardo Barbano, Alexander Denker +1
We present a comprehensive overview of the Deep Image Prior (DIP) framework and its applications to image reconstruction in computed tomography. Unlike conventional deep learning m…
Split, Skip and Play: Variance-Reduced ProxSkip for Tomography Reconstruction is Extremely Fast
Evangelos Papoutsellis, Zeljko Kereta, Kostas Papafitsoros
Many modern iterative solvers for large-scale tomographic reconstruction incur two major computational costs per iteration: expensive forward/adjoint projections to update the data…
Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
Alexander Denker, Moshe Eliasof, Zeljko Kereta +1
Flow-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow ou…
Stochastic Gradient Descent for Nonlinear Inverse Problems in Banach Spaces
Bangti Jin, Zeljko Kereta, Yuxin Xia
Stochastic gradient descent (SGD) and its variants are widely used and highly effective optimization methods in machine learning, especially for neural network training. By using a…