Search Results for author: Mohammad Zalbagi Darestani

Found 4 papers, 4 papers with code

Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing

1 code implementation14 Apr 2022 Mohammad Zalbagi Darestani, Jiayu Liu, Reinhard Heckel

We show that for four natural distribution shifts, this method essentially closes the distribution shift performance gap for state-of-the-art architectures for accelerated MRI.

Compressive Sensing Domain Adaptation +1

Measuring Robustness in Deep Learning Based Compressive Sensing

1 code implementation11 Feb 2021 Mohammad Zalbagi Darestani, Akshay S. Chaudhari, Reinhard Heckel

In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods.

Compressive Sensing Image Reconstruction

Accelerated MRI with Un-trained Neural Networks

3 code implementations6 Jul 2020 Mohammad Zalbagi Darestani, Reinhard Heckel

Convolutional Neural Networks (CNNs) are highly effective for image reconstruction problems.

Image Denoising Image Inpainting +1

Cannot find the paper you are looking for? You can Submit a new open access paper.