AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Monotonicity Prior for Cloud Tomography

Tamar Loeub, Aviad Levis, Vadim Holodovsky, Yoav Y. Schechner

ECCV 2020 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 27 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
add monotonicity prior to smoothness prior (ablation)stochastic cloud tomography · Scene C (small cloud)relative error epsilon (%): 87% -> 84.5%Improved
add monotonicity prior to smoothness prior (ablation)stochastic cloud tomography · Scene C (small cloud)relative bias delta (%): -11.5% -> 5.5%Improved
add monotonicity prior to smoothness prior (ablation)stochastic cloud tomography · Scene F (cloud field)relative error epsilon (%): 54.8% -> 44.7%Improved
add monotonicity prior to smoothness prior (ablation)stochastic cloud tomography · Scene F (cloud field)relative bias delta (%): -34.2% -> -28.2%Improved
use deterministic SHDOM-based tomography instead of Monte Carlo stochastic tomographyscene C reconstruction · Scene C (small cloud)relative error epsilon (%): 84.5% -> 72%Improved
use proposed method instead of MC tomography code based on prior work [15]scene C reconstruction · Scene C (small cloud)relative error epsilon (%): 196% -> 84.5%Improved
use proposed method instead of MC tomography code based on prior work [19]scene C reconstruction · Scene C (small cloud)relative error epsilon (%): 174% -> 84.5%Improved
increase noise in 1D denoising input from N(0,5) to N(0,10)monotonicity prior denoising · 1D denoising examplerelative error epsilon (%): 15% -> 20%Hurt

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