TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving

Key points

• Current methods model lanes as discrete polylines, lacking smoothness, analytical tangent directions, and global spatial support for attention, while providing sparse topology supervision.1
• We propose TopoCurve, a geometry-driven architecture for 3D topology reasoning grounded in a structured parametric lane representation.1
• Lanes are modeled as endpoint-fixed cubic Bézier curves, enabling continuous geometry with exact endpoints and analytically defined directionality.1
• Parallel curve-anchored attention branches provide diverse predictions for one-to-many topology supervision.1

Sources (1)

• [1]TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 09:07 PM

  Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity.

  Current methods model lanes as discrete polylines, lacking smoothness, analytical tangent directions, and global spatial support for attention, while providing sparse topology supervision.

Extractive summary: sentences quoted from the sources.