Wavelet-based Multi-View Fusion of 4D Radar Tensor and Camera for Robust 3D Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guan, Runwei, Liu, Jianan, Liang, Shaofeng, Ding, Fangqiang, Yao, Shanliang, Bai, Xiaokai, Liu, Daizong, Huang, Tao, Mao, Guoqiang, Xiong, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911376587358208
author Guan, Runwei
Liu, Jianan
Liang, Shaofeng
Ding, Fangqiang
Yao, Shanliang
Bai, Xiaokai
Liu, Daizong
Huang, Tao
Mao, Guoqiang
Xiong, Hui
author_facet Guan, Runwei
Liu, Jianan
Liang, Shaofeng
Ding, Fangqiang
Yao, Shanliang
Bai, Xiaokai
Liu, Daizong
Huang, Tao
Mao, Guoqiang
Xiong, Hui
contents 4D millimeter-wave (mmWave) radar has been widely adopted in autonomous driving and robot perception due to its low cost and all-weather robustness. However, point-cloud-based radar representations suffer from information loss due to multi-stage signal processing, while directly utilizing raw 4D radar tensors incurs prohibitive computational costs. To address these challenges, we propose WRCFormer, a novel 3D object detection framework that efficiently fuses raw 4D radar cubes with camera images via decoupled multi-view radar representations. Our approach introduces two key components: (1) A Wavelet Attention Module embedded in a wavelet-based Feature Pyramid Network (FPN), which enhances the representation of sparse radar signals and image data by capturing joint spatial-frequency features, thereby mitigating information loss while maintaining computational efficiency. (2) A Geometry-guided Progressive Fusion mechanism, a two-stage query-based fusion strategy that progressively aligns multi-view radar and visual features through geometric priors, enabling modality-agnostic and efficient integration without overwhelming computational overhead. Extensive experiments on the K-Radar benchmark show that WRCFormer achieves state-of-the-art performance, surpassing the best existing model by approximately 2.4% in all scenarios and 1.6% in sleet conditions, demonstrating strong robustness in adverse weather.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22972
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wavelet-based Multi-View Fusion of 4D Radar Tensor and Camera for Robust 3D Object Detection
Guan, Runwei
Liu, Jianan
Liang, Shaofeng
Ding, Fangqiang
Yao, Shanliang
Bai, Xiaokai
Liu, Daizong
Huang, Tao
Mao, Guoqiang
Xiong, Hui
Computer Vision and Pattern Recognition
Signal Processing
4D millimeter-wave (mmWave) radar has been widely adopted in autonomous driving and robot perception due to its low cost and all-weather robustness. However, point-cloud-based radar representations suffer from information loss due to multi-stage signal processing, while directly utilizing raw 4D radar tensors incurs prohibitive computational costs. To address these challenges, we propose WRCFormer, a novel 3D object detection framework that efficiently fuses raw 4D radar cubes with camera images via decoupled multi-view radar representations. Our approach introduces two key components: (1) A Wavelet Attention Module embedded in a wavelet-based Feature Pyramid Network (FPN), which enhances the representation of sparse radar signals and image data by capturing joint spatial-frequency features, thereby mitigating information loss while maintaining computational efficiency. (2) A Geometry-guided Progressive Fusion mechanism, a two-stage query-based fusion strategy that progressively aligns multi-view radar and visual features through geometric priors, enabling modality-agnostic and efficient integration without overwhelming computational overhead. Extensive experiments on the K-Radar benchmark show that WRCFormer achieves state-of-the-art performance, surpassing the best existing model by approximately 2.4% in all scenarios and 1.6% in sleet conditions, demonstrating strong robustness in adverse weather.
title Wavelet-based Multi-View Fusion of 4D Radar Tensor and Camera for Robust 3D Object Detection
topic Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2512.22972