Saved in:
Bibliographic Details
Main Authors: Wang, Shengpeng, Wang, Kuangyu, Wang, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.01026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917302965895168
author Wang, Shengpeng
Wang, Kuangyu
Wang, Wei
author_facet Wang, Shengpeng
Wang, Kuangyu
Wang, Wei
contents Millimeter-wave radar offers unique advantages in adverse weather but suffers from low spatial fidelity, severe azimuth ambiguity, and clutter-induced spurious returns. Existing methods mainly focus on improving spatial perception effectiveness via coarse-to-fine cross-modal supervision, yet often overlook the ambiguous feature-to-label mapping, which may lead to ill-posed geometric inference and pose fundamental challenges to downstream perception tasks. In this work, we propose RaUF, a spatial uncertainty field learning framework that models radar measurements through their physically grounded anisotropic properties. To resolve conflicting feature-to-label mapping, we design an anisotropic probabilistic model that learns fine-grained uncertainty. To further enhance reliability, we propose a Bidirectional Domain Attention mechanism that exploits the mutual complementarity between spatial structure and Doppler consistency, effectively suppressing spurious or multipath-induced reflections. Extensive experiments on public benchmarks and real-world datasets demonstrate that RaUF delivers highly reliable spatial detections with well-calibrated uncertainty. Moreover, downstream case studies further validate the enhanced reliability and scalability of RaUF under challenging real-world driving scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01026
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RaUF: Learning the Spatial Uncertainty Field of Radar
Wang, Shengpeng
Wang, Kuangyu
Wang, Wei
Computer Vision and Pattern Recognition
Millimeter-wave radar offers unique advantages in adverse weather but suffers from low spatial fidelity, severe azimuth ambiguity, and clutter-induced spurious returns. Existing methods mainly focus on improving spatial perception effectiveness via coarse-to-fine cross-modal supervision, yet often overlook the ambiguous feature-to-label mapping, which may lead to ill-posed geometric inference and pose fundamental challenges to downstream perception tasks. In this work, we propose RaUF, a spatial uncertainty field learning framework that models radar measurements through their physically grounded anisotropic properties. To resolve conflicting feature-to-label mapping, we design an anisotropic probabilistic model that learns fine-grained uncertainty. To further enhance reliability, we propose a Bidirectional Domain Attention mechanism that exploits the mutual complementarity between spatial structure and Doppler consistency, effectively suppressing spurious or multipath-induced reflections. Extensive experiments on public benchmarks and real-world datasets demonstrate that RaUF delivers highly reliable spatial detections with well-calibrated uncertainty. Moreover, downstream case studies further validate the enhanced reliability and scalability of RaUF under challenging real-world driving scenarios.
title RaUF: Learning the Spatial Uncertainty Field of Radar
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.01026