AI Paper Atlas

Research map / Point clouds / Point cloud classification

CPO: Change Robust Panorama to Point Cloud Localization

Junho Kim, Hojun Jang, Changwoon Choi, Young Min Kim

ECCV 2022 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 6 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 histogram-based candidate pose selection (ablation)CPO · OmniScenes Extremeaccuracy: 0.20 -> 0.57Improved
add histogram-based candidate pose selection (ablation)CPO · OmniScenes ExtremeR-error (deg): 75.60 -> 0.37Improved
add 2D score map for candidate pose selection (ablation)CPO · OmniScenes Extremeaccuracy: 0.48 -> 0.57Improved
add 2D score map (ablation)CPO · OmniScenes Extremet-error (m): 0.10 -> 0.03Improved
add 3D score map for weighted sampling loss (ablation)CPO · OmniScenes Extremeaccuracy: 0.55 -> 0.57Improved
add 3D score map (ablation)CPO · OmniScenes ExtremeR-error (deg): 1.56 -> 0.37Improved
use fast histogram generation versus rendering-based initialization of baselinesCPO · OmniScenes Room 3runtime per view (ms): 38.70 -> 0.188Improved
replace PICCOLO with CPO score-map pipelinePICCOLO · OmniScenes Robotaccuracy: 0.06 -> 0.58Improved
give PICCOLO a gravity priorPICCOLO · OmniScenes Robotaccuracy: 0.06 -> 0.39Improved
CPO versus structure-based methodStructure-Based · Structured3Daccuracy (0.05m, 5deg): 0.59 -> 0.56No clear effect
CPO versus structure-based method at tight thresholdStructure-Based · Structured3Daccuracy (0.01m, 1deg): 0.29 -> 0.51Improved
CPO versus PICCOLO on Stanford 2D-3D-SPICCOLO · Stanford 2D-3D-Saccuracy: 0.53 -> 0.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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