Research papers · Posted 2025.07.31 · Preprint

PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving

Xuewei Tang, Mengmeng Yang, Tuopu Wen, Peijin Jia, Le Cui, Mingshang Luo, Kehua Sheng, Bo Zhang, Diange Yang, Kun Jiang · arXiv · English

Overview

PriorFusion integrates semantic, geometric and generative priors for road-element perception. Shape templates and diffusion-based prediction are evaluated for more coherent outputs under occlusion and complex road geometry without relying on HD maps.

Version: v2

PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving

Overview

Participation enquiry

Your enquiry has been sent.

PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving

Overview

Related resources

UECP: Uncertainty-Enhanced Collaborative Perception

Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception

A Task-Agnostic Algebraic Integrity Metric for Event-Camera Streams Toward SOTIF-Compliant Perception using Pearson Correlation Coefficient