AI Paper Atlas

Research map / 3D vision / 3D generation

HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection

Jiyong Boo, ByeongIn Joung, Hyemin Yang, KUK-JIN YOON

ECCV 2026 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 0 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
replace direct height regression with HSDF formulation (ablation)HSDF-Lane · OpenLane (full, height map)overall MAE: 0.183 -> 0.159Improved
add height-directional Eikonal regularization (ablation)HSDF-Lane · OpenLane (full, height map)overall RMSE: 0.347 -> 0.331Improved
add Eikonal regularization on top of height supervision (ablation)HSDF-Lane · OpenLane-300F1-score (%): 74.2 -> 74.7Improved
add explicit height map supervision L_H (ablation)HSDF-Lane · OpenLane-300F1-score (%): 71.8 -> 74.2Improved
add LSPE (ablation)HSDF-Lane · OpenLane-300F1-score (%): 74.7 -> 75.6Improved
add LSPE (single learnable vector gated by heatmap) (ablation)HSDF-Lane · OpenLane val (full)F1-score (%): 65.9 -> 66.3Improved
encode heatmap with full learnable MLP instead of single vector (ablation)LSPE · OpenLane val (full)F1-score (%): 66.3 -> 65.7Hurt
concatenate heatmap instead of gating a learnable vector (ablation)LSPE · OpenLane val (full)F1-score (%): 66.3 -> 66.0Hurt
vary max slope angle theta from 5 to 4 or 6 degrees (ablation)HSDF-Lane · OpenLane-300F1-score (%): 75.6 -> 75.6 (theta 4), 75.6 -> 74.8 (theta 6)Hurt
use FPN multi-scale features with 4-layer decoderHSDF-Lane · OpenLane valF1-score (%): 66.3 -> 66.9Improved
replace dense LiDAR height supervision with lane-derived pseudo heights (ablation)HSDF-Lane · OpenLane valF1-score (%): 66.3 -> 66.0No clear effect
replace anchor-based height regression with HSDF dense samplingHeightLane/SC-Lane · OpenLane height mapMAE: 0.176 -> 0.158 (vs SC-Lane)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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