AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses

Eric Brachmann, Carsten Rother

ICCV 2019 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 280 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 neural guidance to RANSAC samplingRANSAC · Essential matrix, outdoor and indoor (no side information)AUC of pose errorImproved
train with pose-error task loss instead of hybrid classification-regression lossNG-RANSAC vs InClass · Essential matrix, outdoor and indoorAUC of pose errorImproved
apply Lowe ratio filter (0.8) to correspondencesRANSAC, USAC and learned methods · Essential matrix, outdoor and indoorAUC of pose errorImproved
add distance ratios as extra network input (+SI) with RootSIFT (ablation)NG-RANSAC · Essential matrix, outdoor and indoorAUC of pose errorImproved
pass NG-RANSAC learned weights to USAC instead of matching ratios (ablation)USAC · Essential matrix, outdoor, no ratio filter, M=10^3AUC (5/10/20 deg): -0.27/-0.24/-0.34Hurt
train self-supervised with inlier count instead of ground-truth pose loss (ablation)NG-RANSAC · Essential matrix, outdoor and indoorAUC of pose errorHurt
increase hypothesis count from M=10 to M=10^3 (ablation)NG-RANSAC · Essential matrix runtimeruntime per image pair: 21ms -> 90msHurt
choice of training objective (%Inliers, F-score, Mean error) (ablation)NG-RANSAC · Kitti fundamental matrixinlier %, F-score, epipolar errorNo clear effect
add neural guidance to DSACDSAC · HLW horizon line estimationAUCImproved
add neural guidance to RANSAC for fundamental matrixRANSAC and USAC · Kitti fundamental matrixinlier %, F-scoreImproved

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