AI Paper Atlas

Research map / Point clouds / Point cloud classification

Space-Partitioning RANSAC

Daniel Barath, Gábor Valasek

ECCV 2022 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 8 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 space-partitioning verificationLO-RANSAC · Homography (Sacre Coeur), no SPRTverification time (ms): 88.8 -> 40.0Improved
add space-partitioning verificationLO-RANSAC · Fundamental matrix, no SPRTverification time (ms): 113.7 -> 50.3Improved
add space-partitioning verificationLO-RANSAC · Essential matrix, no SPRTverification time (ms): 537.6 -> 251.2Improved
add space-partitioning verification on top of SPRTLO-RANSAC with SPRT · Essential matrixverification time (ms): 79.7 -> 29.4Improved
add space-partitioning verification on top of SPRTLO-RANSAC with SPRT · Radial homography (Sun360)average run-time (ms): 331.3 -> 134.7Improved
add space-partitioning verification on top of SPRTLO-RANSAC with SPRT · Homography (Sacre Coeur)average run-time (ms): 39.3 -> 31.2Improved
add space-partitioning verificationLO-RANSAC · Essential matrixAUC@10: 0.65 -> 0.65No clear effect
add space-partitioning verification to SPRTLO-RANSAC with SPRT · Essential matrixAUC@10: 0.61 -> 0.63Mixed
raise early rejection threshold above 1 (1.6) for homography (ablation)space-partitioning RANSAC · Homographyrun-time: approximately 20% lower run-timeImproved
raise early rejection threshold to 1.2 for F and E (ablation)space-partitioning RANSAC · Fundamental and essential matrixprocessing time: 22% and 9% lowerImproved
use more grid cells (beyond 16) for F estimation (ablation)space-partitioning RANSAC · Fundamental matrixrun-time: 16 cells fastest; time increases with cell numberHurt
use 256 cells instead of other cell counts (ablation)space-partitioning RANSAC · Homographyrun-time: 50% of traditional run-time at 10000 iterationsImproved

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