AI Paper Atlas

Research map / 3D vision / 3D generation

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, Feng Wen, Hang Xu and 4 more

NeurIPS 2023 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 18 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
Use TopoNet instead of the strongest other listed method, STSUscene structure perception models · OpenLane-V2 subset_A valOLS: 25.4 -> 35.4Improved
Use TopoNet instead of the strongest other listed method, MapTRscene structure perception models · OpenLane-V2 subset_B valOLS: 21.1 -> 33.2Improved
Use TopoNet instead of STSUscene structure perception models · OpenLane-V2 subset_A valDET_l: 12.7 -> 29.2Improved
Use TopoNet instead of MapTRscene structure perception models · OpenLane-V2 subset_B valDET_l: 8.3 -> 24.3Improved
Represent centerlines as point sets rather than instance-level queriescenterline prediction models · OpenLane-V2 subset_A valOLS: 25.4 -> 20.8; 35.4 -> 20.0Mixed

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