Skip to content
Open access

Expert-Consistency-Guided Proposal Refinement for 3D Object Detection from Sparse Radar Point Clouds

Oct 2026 · Italian National Conference on Sensors · Vol 26 · 0 citations · 55 references
Medicine

TL;DR

An expert-consistency-guided refinement framework that acts on detector outputs without changing the backbone, which shows metric-dependent confidence–calibration trade-offs and requires an additional expert detector and voting computation.

Abstract

Sparse radar point clouds provide limited evidence for three-dimensional (3D) object detection, making weak proposals especially sensitive to ranking and suppression. Standard post-processing depends on the primary detector’s scores and geometry and can therefore remove useful candidates. We introduce an expert-consistency-guided refinement framework that acts on detector outputs without changing the backbone. Candidate boxes are retained and reweighted according to agreement with an independently trained radar expert; supported boxes are then adjusted by local geometric voting. A separate high-performance route instead trains a localization-quality-aware confidence head with relaxed positive assignment and does not use the expert-consistency gate. The framework is evaluated on Astyx, MAN TruckScenes, V2X-Radar-V, and K-Radar with three training seeds. At a 3D intersection-over-union threshold of 0.50, the strict route improves average precision (AP) in all 12 matched dataset–seed comparisons, with a mean gain of 0.9726 AP. The high-performance route, whose gain comes from this quality-aware ranking branch rather than from expert-consistency gating, raises macro AP from 35.3552 to 39.1214, a gain of 3.7662 AP. These improvements are observations under the evaluated protocol: the strict voting parameters were selected using the same dataset–seed cells, and leave-one-dataset-out threshold selection yields 11/12 positive held-out differences. The strict route also shows metric-dependent confidence–calibration trade-offs and requires an additional expert detector and voting computation. The results therefore support protocol-specific gains, not a guarantee of improved reliability on unseen data.

Read PDF

Similar papers

Conference Oct 2026

LiDAR-based 3D object detection with localization reliability enhancement based on CenterPoint

3D object detection from LiDAR point clouds is a fundamental perception task in autonomous driving, aiming to accurately localize and classify surrounding objects in sparse and irregular point-cloud data. CenterPoint is a widely adopted anchor-free baseline for LiDAR-based 3D object detection, but it often suffers from...

Jia-Wei Lin · 0 citations
Preprint Sep 2026

GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection

Long-tailed 3D object detection is treated as a class-frequency problem, but LiDAR supervision quality depends on object observability: similar frequencies can hide different geometric evidence. We introduce Geometry-Augmented Exponentially Weighted Instance-Aware Repeat Factor Sampling (GA-EIRFS), a detector-agnostic...

Taufiq Ahmed, C. A. Casado, Daniel Herrera Castro et al. · 0 citations
Preprint Sep 2026

SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection

4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve \emph{where} to align the modalities while leaving \emph{whether} a piece of evidence supports an evolving object hypothesis implicit. An image token may describe an occluder, a near...

Xiao-Kai Bai, Zhen-Yu Fan, Lian-Qing Zheng et al. · 0 citations
Open access Oct 2026

Few-Shot Aircraft Door Detection with Visibility-Aware Geometric Regularization

Aircraft-door detection is a key perception component for automated passenger boarding bridges, but its performance can degrade substantially under limited annotations, illumination changes, partial occlusion, and viewpoint variation. To address this problem, we propose a multi-constraint geometric regularization (MGR)...

Le-Xian Liang, Hai-Long Pei · 0 citations
Preprint Sep 2026

Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection

A multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection that indicates that a stable, interpretable collaboration among data sources is more valuable than unconstrained aggregation of model outputs.

Pu Luo, Cong Xu, Yu-Mei Li et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.