DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather

TL;DR

DinoRADE is a radar-camera fusion method using vision foundation model features that improves multi-class object detection, especially for vulnerable road users, in adverse weather conditions.

Contribution

It introduces a Radar-centered detection pipeline with deformable cross-attention and leverages DINOv3 features, achieving superior performance on the K-Radar dataset.

Findings

Outperforms recent Radar-camera approaches by 12.1%.

Provides detection performance for five object classes in all weather conditions.

First to report individual detection performance for VRUs in adverse weather.

Abstract

Reliable and weather-robust perception systems are essential for safe autonomous driving and typically employ multi-modal sensor configurations to achieve comprehensive environmental awareness. While recent automotive FMCW Radar-based approaches achieved remarkable performance on detection tasks in adverse weather conditions, they exhibited limitations in resolving fine-grained spatial details particularly critical for detecting smaller and vulnerable road users (VRUs). Furthermore, existing research has not adequately addressed VRU detection in adverse weather datasets such as K-Radar. We present DinoRADE, a Radar-centered detection pipeline that processes dense Radar tensors and aggregates vision features around transformed reference points in the camera perspective via deformable cross-attention. Vision features are provided by a DINOv3 Vision Foundation Model. We present a comprehensive performance evaluation on the K-Radar dataset in all weather conditions and are among the first to report detection performance individually for five object classes. Additionally, we compare our method with existing single-class detection approaches and outperform recent Radar-camera approaches by 12.1%. The code is available under https://github.com/chr-is-tof/RADE-Net.