AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching

Johannes L. Schonberger, Sudipta N. Sinha, Marc Pollefeys

ECCV 2018 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 55 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 learned random-forest fusion of scanline proposals instead of summationSGM · Middlebury 2014 trainingbad 1px: 23.04 -> 19.99Improved
pick min-cost scanline instead of sumSGM · Middlebury 2014 trainingbad 1px: 23.04 -> 25.45Hurt
use median across scanlines instead of sumSGM · Middlebury 2014 trainingbad 1px: 23.04 -> 31.81Hurt
add the diagonal scanlines to horizontal and vertical proposals (ablation)SGM-Forest · Middlebury 2014 trainingbad 1px: 21.30 -> 20.85Improved
use all 8 scanlines instead of only top-down (ablation)SGM-Forest · Middlebury 2014 trainingbad 1px: 21.20 -> 20.85Improved
add right-view scanline proposals or filtering step (ablation)SGM-Forest · Middlebury 2014 trainingbad 4px: 4.89 -> 4.72Improved
use random forest instead of linear SVM (ablation)SGM-SVM · Middlebury 2014 trainingbad 1px: 21.88 -> 20.85Improved
use random forest instead of MLP (ablation)SGM-MLP · Middlebury 2014 trainingbad 1px: 21.83 -> 20.85Improved
train on KITTI instead of Middlebury 2005-06 (ablation)SGM-Forest full · Middlebury 2014 trainingbad 1px: 19.99 -> 20.45No clear effect
train on ETH3D instead of Middlebury 2005-06 (ablation)SGM-Forest full · Middlebury 2014 trainingbad 1px: 19.99 -> 20.32No clear effect
replace SGM with SGM-Forest using NCC costSGM · KITTI 2015bad 4px: 6.17 -> 4.17Improved
replace SGM with SGM-Forest using MC-CNN-fastSGM · ETH3D 2017 bad 1pxbad 1px: 8.56 -> 6.08Improved

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