AI Paper Atlas

Research map / 3D vision / Face and shape

3DeepCT: Learning Volumetric Scattering Tomography of Clouds

Yael Sde-Chen, Yoav Y. Schechner, Vadim Holodovsky, Eshkol Eytan

ICCV 2021 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 24 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
reduce viewpoints from 32 to 103DeepCT · BOMEXrelative average error epsilon (%): 82 -> 86Hurt
reduce viewpoints from 32 to 103DeepCT · BOMEXrelative total mass error delta (%): 32 -> 44Hurt
use 3DeepCT instead of physics-based inverse scatteringSHDOM inversion · 7-cloud subset, 32 viewpointsrun time: about five orders of magnitude fasterImproved
use 3DeepCT instead of physics-based inverse scatteringSHDOM inversion · 7-cloud subset, 32 viewpointsreconstruction errorImproved
initialize physics-based inversion with 3DeepCT output (hybrid)SHDOM inversion · 7-cloud subset, 32 viewpointsreconstruction errorImproved
shorten hybrid to 10 physics iterations (quick hybrid)Hybrid system · 7-cloud subset, 32 viewpointsquality and run timeMixed
train on CASS (larger fields) with Model 33DeepCT · CASS 64x64 voxelsscalabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy