Seminar: Pixel Club

ECE Women Community

3DeepCT: Learning Volumetric Scattering Tomography of Clouds

Date: September,14,2021 Start Time: 11:30 - 12:30
Location: zoom
Add to:
Lecturer: Yael Sde Chen
Affiliations: The Andre and Erna Vitervi Faculty of Electrical & Computer Engineering

We present 3DeepCT, a deep neural network for computed tomography, which performs 3D reconstruction of scattering volumes from multi-view images.

The architecture is dictated by the stationary nature of atmospheric cloud fields.

The task of volumetric scattering tomography aims at recovering a volume from its 2D projections. This problem has been approached by diverse inverse methods based on signal processing and physics models. However, such techniques are typically iterative, exhibiting a high computational load and a long convergence time.

We show that 3DeepCT outperforms physics-based inverse scattering methods, in  accuracy, as well as offering orders of magnitude improvement in computational run-time. We further introduce a hybrid model that combines 3DeepCT and physics-based analysis. The resultant hybrid technique enjoys fast inference time and improved recovery performance.

 

* M.Sc. Under the supervision of Prof. Yoav Schechner.

 

 

All Seminars
Skip to content