AI Paper Atlas

Research map / 3D vision / 3D generation

End-to-End Deep Structured Models for Drawing Crosswalks

Justin Liang, Raquel Urtasun

ECCV 2018 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 25 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 camera to LiDAR inputcrosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 95.8 -> 96.6Improved
add LiDAR to camera inputcrosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 94.9 -> 96.6Improved
use multiple passes instead of a single passcrosswalk model · camera+LiDARprecision at 40cm: 91.5 -> 96.6Improved
add structured inference over CNN segmentation outputcrosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 93.1 -> 96.6Improved
add structured prediction over nearest neighbor on VGG featurescrosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 24.8 -> 96.6Improved
add +-2 and +-5 degree angle search (ablation)structured inference · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 94.4 -> 96.6Improved
add centerline angle hypothesis (ablation)structured inference · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 96.3 -> 96.6Improved
add predicted angle from CNN (ablation)structured inference · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 85.3 -> 96.6Improved
use ground-truth segmentation (ablation)crosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 96.6 -> 97.8Improved
use ground-truth distance transform (ablation)crosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 96.6 -> 96.6No clear effect
use ground-truth angle (ablation)crosswalk model · Crosswalk dataset test (offline, multi-pass)precision at 40cm: 96.6 -> 96.5No clear effect
retrain with images without crosswalkscrosswalk model · images without crosswalksfalse positive rate: 5.7% -> 0.04%Improved

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