Publications (selected)

2021

Learning-based Motion Artifact Removal Networks (LEARN) for Quantitative R2* Mapping

Xiaojian Xu, Satya V.V.N. Kothapalli, Jiaming Liu, Sayan Kahali, Weijie, Dmitriy Yablonskiy, U. S. Kamilov

Deep-Learning-Based Accelerated and Noise-Suppressed Estimation (DANSE) of quantitative Gradient Recalled Echo (qGRE) MRI metrics associated with Human Brain Neuronal Structure and Hemodynamic Properties

Sayan Kahali, Satya V.V.N. Kothapalli, Xiaojian Xu, U. S. Kamilov Dmitriy Yablonskiy

SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees

Jiaming Liu, Yu Sun, Weijie, Xiaojian Xu, Brendt Wohlberg, U. S. Kamilov

IEEE TCI / ICASSP / arXiv

2020

Scalable Plug-and-Play ADMM with Convergence Guarantees

Xiaojian Xu*, Yu Sun*, Zihui Wu*, Brendt Wohlberg, U. S. Kamilov

Provable Convergence of Plug-and-Play Priors With MMSE Denoisers

Xiaojian Xu, Yu Sun, Jiaming Liu, Brendt Wohlberg, U. S. Kamilov

IEEE SPL / arXiv

Boosting the performance of plug-and-play priors via denoiser scaling

Xiaojian Xu, Jiaming Liu, Yu Sun, Brendt Wohlberg, U. S. Kamilov

Asilomar 2020 / arXiv / slides

Oral presentation

Robust 3D Tomographic Imaging of the Iononspheric Electron Density

Xiaojian Xu, Oussama Dhifallah, Hassan Mansour, Petros Boufounos, Philip Orlik

IGARSS 2020 / MERL / slides

Oral presentation

2019

Signprox: One-bit proximal algorithm for nonconvex stochastic optimization

Xiaojian Xu, U. S. Kamilov

ICASSP 2019 / arXiv / slides

Oral presentation

Image Restoration Using Total Variation Regularized Deep Image Prior

Jiaming Liu, Yu Sun, Xiaojian Xu, U. S. Kamilov

ICASSP 2019 / arXiv / poster