AI Paper Atlas

Research map / Detection and segmentation / CNN features

ELSD: Efficient Line Segment Detector and Descriptor

Haotian Zhang, Yicheng Luo, Fangbo Qin, Yijia He, Xiao Liu

ICCV 2021 · Detection and segmentation › CNN features · approach: Lane detection · 47 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 non-centerness suppression (ablation)ELSD · WireframesAP10: 68.0 -> 68.9Improved
add descriptor branch with joint training (ablation)ELSD · WireframesAP10: 68.9 -> 68.5No clear effect
upsample prediction maps to 256 resolution (ablation)ELSD · WireframesAP10: 65.8 -> 68.9Improved
use focal loss instead of BCE for midpoint map (ablation)ELSD · WireframesAP10: 66.0 -> 68.9Improved
use CAL representation instead of Tri-points (ablation)ELSD · WireframesAP10: 67.9 -> 68.9Improved
all four components together versus none (ablation)ELSD · WireframesAP10: 62.8 -> 68.9Improved
use 64-d descriptor instead of 36-d (ablation)ELSD · WireframeF-score: 73.7 -> 74.8Improved
use 64-d descriptor instead of 256-dELSD · Line matching (ScanNet subset)F-score: 74.7 -> 74.8No clear effect
replace ResNet34 backbone with HourglassELSD · WireframesAP10: 68.9 -> 67.2Hurt
shrink to Lite version (256 input)ELSD · WireframesAP10: 68.9 -> 63.1Hurt

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