Projects

I have been working on diffusion and generative modeling for solving complex inverse problems in imaging and signal reconstruction. My work explores how self-diffusion processes and autoregressive diffusion architectures can recover high-fidelity data while providing principled uncertainty estimation.

I bridge deep generative modeling, Bayesian inference, and software engineering, developing models that move seamlessly from theory to deployment. Using frameworks like PyTorch, TensorFlow, and TensorRT, I build full-stack systems that make cutting-edge generative methods practical for real-world applications.

DeblurSDI: blind image deblurring using self-diffusion

Computational imaging, Blind image deblur, Self-diffusion model, Inverse problem

Self-diffusion for solving inverse problems

diffusion models, inverse problem, lower level vision, MRI reconstruction

Autogressive image diffusion: generation of image sequences and application in MRI reconstruction

autoregressive, diffusion models, image sequences, inverse problem, MRI reconstruction

Bayesian MRI reconstruction with joint uncertainty estimation using diffusion models

sampling posterior, Bayesian inference, diffusion models, uncertainty estimation, inverse problem, MR image reconstruction, Monte Carlo, Markov chain

Generative Image Priors for MRI Reconstruction Trained from Magnitude-Only Images

generative pretraining, image priors, diffusion models, inverse problem, MR image reconstruction, proximal operator, optimization

Deploy generative image priors for image reconstruction using BART

MR image reconstruction, model deployment, TensorFlow C API, TensorFlow computation graph

MRI reconstruction using deep Bayesian estimation

generative model, PixelCNN, Bayesian estimation, MR image reconstruction, optimization

Generalized deep learning-based proximal gradient descent for MR reconstruction

MR image reconstruction, proximal gradient descent, denoising autoencoder