AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Improving Online Lane Graph Extraction by Object-Lane Clustering

Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, Luc Van Gool

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 10 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 object clustering loss (ablation)lane graph model with DeepInteraction objects · NuScenesM-F: 63.2 -> 64.2Improved
add object clustering loss (ablation)lane graph model with BEVFusion objects · NuScenesM-F: 63.4 -> 63.9Improved
add object clustering loss (ablation)lane graph model with GT objects · NuScenesM-F: 63.8 -> 64.2Improved
add object clustering loss (ablation)lane graph model with CBGS objects · ArgoverseM-F: 67.6 -> 68.9Improved
add object clustering loss (ablation)lane graph model with GT objects · ArgoverseDetect: 71.0 -> 71.0No clear effect
add object center refinement alone to the lane graph model (ablation)lane graph model with DeepInteraction objects · NuScenesM-F: 63.2 -> 63.2No clear effect
add refinement together with clustering loss (ablation)lane graph model with DeepInteraction objects · NuScenesM-F: 64.2 -> 64.8Improved
add lane graph supervision to object refinement training (ablation)refinement module with DeepInteraction objects · NuScenesmAP: 47.8 -> 58.6Improved
refine object centers vs original detectorDeepInteraction · NuScenesmAP: 69.8 -> 58.9Hurt
test with different object detector than used in training (ablation)lane graph model trained with BEVFusion objects · NuScenesM-F: 64.9 -> 64.8No clear effect
test model trained on detections with ground-truth objects (ablation)lane graph model trained with BEVFusion objects · NuScenes object clustering accuracyaccuracy (%): 90.3 -> 83.9Hurt

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