AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

Bencheng Liao, Shaoyu Chen, Bo Jiang, Tianheng Cheng, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 60 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
model the lane graph as continuous paths instead of pieces (MapTR with same decoder)MapTR piece-wise · nuScenes valJunction TOPO F1: 0.496 -> 0.564Improved
path-wise modeling versus pixel-wise segmentation modelingHDMapNet · nuScenes valTOPO F1 and FPS: TOPO F1 0.513 -> 0.529; FPS 6.8 -> 15.6Improved
adapt TopoNet lane detection to path-wise representationTopoNet · OpenLane-V2mIoU: 39.0 -> 40.6Improved
add auxiliary BEV segmentation loss (ablation)LaneGAP · nuScenes val (24 epochs)Junction TOPO F1: 0.529 -> 0.539Improved
increase polyline points from 10 to 40 (ablation)LaneGAP · nuScenes val (24 epochs)Junction TOPO F1: 0.532 -> 0.557Improved
increase Bezier control points from 5 to 10 (ablation)LaneGAP · nuScenes val (24 epochs)Junction TOPO F1: 0.510 -> 0.501Hurt
increase Bezier control points from 3 to 5 (ablation)LaneGAP · nuScenes val (24 epochs)Junction TOPO F1: 0.481 -> 0.510Improved
replace MapTR centerline map branch with LaneGAP path queries in end-to-end plannerVAD-Tiny · nuScenes planningavg L2 (m): 0.74 -> 0.70Improved
add LiDAR modality to vision (ablation)LaneGAP · nuScenes (24 epochs)Junction TOPO F1: 0.539 -> 0.615Improved
train longer (110 vs 24 epochs) (ablation)LaneGAP vision-only · nuScenesJunction TOPO F1 vs TOPO F1: Junction 0.539 -> 0.564; TOPO 0.461 -> 0.529Mixed
use path-wise instead of pixel-wise modeling on precision of junction TOPOHDMapNet · Argoverse2Junction TOPO precision: 0.656 -> 0.663No clear effect

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