3DeepCT: Learning Volumetric Scattering Tomography of Clouds

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 volum...

Full description

Saved in:
Bibliographic Details
Main Authors: Sde-Chen, Yael, Schechner, Yoav Y., Holodovsky, Vadim, Eytan, Eshkol
Format: Conference Proceeding
Language:English
Subjects:
3D from multiview and other sensors
and cell microscopy
Atmospheric modeling
biological
Clouds
Computational modeling
Inverse problems
Low-level and physics-based vision
Medical
Scattering
Signal processing
Stereo
Three-dimensional displays
Vision applications and systems
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00562