AI Paper Atlas

Research map / Point clouds / Point cloud classification

DPDist: Comparing Point Clouds Using Deep Point Cloud Distance

Dahlia Urbach, Yizhak Ben-Shabat, Michael Lindenbaum

ECCV 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 42 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
increase global Gaussian grid from 4^3 to 8^3 (ablation)DPDist (local 3^3) · ModelNet40 chair reconstructionChamfer L1: 0.130189 -> 0.071805Improved
increase global Gaussian grid from 8^3 to 16^3 (ablation)DPDist (local 3^3) · ModelNet40 chair reconstructionChamfer L1: 0.071805 -> 0.058943Improved
increase global Gaussian grid from 8^3 to 16^3 (ablation)DPDist (local 3^3) · ModelNet40 chair reconstructionNormal consistency: 0.794560 -> 0.809462Improved
increase local patch grid from 1^3 to 3^3 (ablation)DPDist (global 8^3) · ModelNet40 chair reconstructionChamfer L1: 0.103590 -> 0.071805Improved
increase local patch grid from 3^3 to 5^3 (ablation)DPDist (global 8^3) · ModelNet40 chair reconstructionNormal consistency: 0.794560 -> 0.739863Hurt
increase local patch grid from 3^3 to 5^3 (ablation)DPDist (global 8^3) · ModelNet40 chair reconstructionChamfer L1: 0.071805 -> 0.072714No clear effect
use DPDist instead of Chamfer distance for translation detectionDPDist · Sydney Urban carstransformation distance (mean): 0.02879 -> 0.01385Improved
use DPDist instead of EMD for translation detectionDPDist · Sydney Urban carstransformation distance (mean): 0.02381 -> 0.01385Improved
use DPDist instead of partial Hausdorff PH8DPDist · Sydney Urban carstransformation distance (mean): 0.00863 -> 0.01385Hurt
use DPDist instead of Chamfer as PCRNet training lossPCRNet · ModelNet40 chair registration, N=64,128,1024success ratioImproved
use DPDist loss instead of Chamfer when the two clouds are identical samplesPCRNet · ModelNet40 chair registration, N=128 identical cloudssuccess ratioNo clear effect
use DPDist instead of Chamfer as auto-encoder lossPointNet auto-encoder · ModelNet40, N=128point coverageHurt

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