Modular and scalable computational imaging in Python with GPU/out-of-core computing.

Official repository for "Regularization by Texts for Latent Diffusion Inverse Solvers" (ICLR2025 spotlight)

Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction

Plug-and-Play ADMM scheme based on an adaptive denoiser using the Schroedinger equation's solutions of quantum physics.

Signal and image denoising using quantum adaptive transformation.

Differentiable N-body code (JAX)

MicroInverse is a Python package for inversion of a transport operator from tracer data

Xin's insights into computational optics

Deep Denoising by Quantum Interactive Patches. A deep neural network called DIVA unfolding a baseline adaptive denoising algorithm (De-QuIP), relying on the theory of quantum many-body physics.

Digital Twins for Computational Oncology

Offical Pytorch Implementation of EnKG

Denoising by Quantum Interactive Patches

Interactive MATLAB-based SEIRSVBH Simulator for COVID-19 modeling and analysis. Performs error quantification, parameter estimation, and direct simulations using officially reported data for Bulgaria (2020–2023).

🎼 DiffMusic: A Training-Free Diffusion Framework for Music Inverse Problem

Bayesian model reconstruction based on astronomical spectral line observations.

Single image super resolution algorithm RED+ADMM+De-QuIP

Code for generating deep learning data through X-ray tomography for object detection

laura: Local Auto-Regressive Average: A linear solution to the M/EEG inverse problem

Temporal laser-pulse-shape effects in nonlinear Thomson scattering

A solver of EEG/MEG inverse problem using a multivariate auto-regressive model on the source space

Differentiable cortical folding simulator in JAX for forward mechanics and inverse growth-field recovery.

This repository implements a Reinforcement Learning (RL) framework to solve the inverse bone remodeling problem. While the forward problem predicts bone density changes from known loads, this project utilizes Proximal Policy Optimization (PPO) to identify unknown mechanical loading conditions from observed bone morphology.

Python port of Redbird - a comprehensive DOT image reconstruction toolbox

crEITive is a software tool for complex geometrical optics reconstruction for the 3D Calderón problem

Inverse Decomposition of Energy Consumption (NILM)

Extrapolation Volumique de Mesures Surfaciques (EVMS)

Input a vibrational spectrum and watch as an ML model predicts the most likely molecular structure in 3D.

Multiscale Bayesian framework bridging 5-species oral biofilm ecology and 3D FEM stress analysis via TMCMC, DeepONet surrogate (~100x speedup), and GNN-informed priors. 28x stiffness range, basin sensitivity, gradient-based NUTS sampling.

Project for the Computational Imaging course 2024/2025.

MATLAB implementation of "Fourier Phase Retrieval with Arbitrary Reference Signal" paper accepted at IEEE ICASSP 2020.