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

TL;DR

PriorFusion is a novel framework that integrates semantic, geometric, and generative priors using an attention mechanism and diffusion models to improve road perception accuracy in autonomous driving, especially in complex, occluded environments.

Contribution

It introduces a unified approach combining multiple priors and a diffusion-based framework for enhanced road element perception in autonomous driving.

Findings

Significantly improves perception accuracy in challenging scenarios.

Produces more regular and coherent predictions of road elements.

Demonstrates superior performance on large-scale datasets.

Abstract

With the growing interest in autonomous driving, there is an increasing demand for accurate and reliable road perception technologies. In complex environments without high-definition map support, autonomous vehicles must independently interpret their surroundings to ensure safe and robust decision-making. However, these scenarios pose significant challenges due to the large number, complex geometries, and frequent occlusions of road elements. A key limitation of existing approaches lies in their insufficient exploitation of the structured priors inherently present in road elements, resulting in irregular, inaccurate predictions. To address this, we propose PriorFusion, a unified framework that effectively integrates semantic, geometric, and generative priors to enhance road element perception. We introduce an instance-aware attention mechanism guided by shape-prior features, then construct a data-driven shape template space that encodes low-dimensional representations of road elements, enabling clustering to generate anchor points as reference priors. We design a diffusion-based framework that leverages these prior anchors to generate accurate and complete predictions. Experiments on large-scale autonomous driving datasets demonstrate that our method significantly improves perception accuracy, particularly under challenging conditions. Visualization results further confirm that our approach produces more accurate, regular, and coherent predictions of road elements.