Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses

ICCV 2019 Eric BrachmannCarsten Rother

We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Horizon Line Estimation Horizon Lines in the Wild NG-DSAC AUC (horizon error) 75.2 # 1