Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Deng, Jianning, Chan, Gabriel, Zhong, Hantao, Lu, Chris Xiaoxuan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910363497267200
author Deng, Jianning
Chan, Gabriel
Zhong, Hantao
Lu, Chris Xiaoxuan
author_facet Deng, Jianning
Chan, Gabriel
Zhong, Hantao
Lu, Chris Xiaoxuan
contents This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple alignments on both spatial and feature levels to achieve simultaneous backbone refinement and hallucination generation. Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar. The feature alignment step further bridges the intrinsic attribute gap between the sensing modalities and stabilizes the training. The trained object detection models can deal with difficult detection cases better, even though only single-modal data is used as the input during the inference stage. Extensive experiments on the View-of-Delft (VoD) dataset show that our proposed method outperforms the state-of-the-art (SOTA) methods for both radar and LiDAR object detection while maintaining competitive efficiency in runtime. Code is available at https://github.com/DJNing/See_beyond_seeing.
format Preprint
id arxiv_https___arxiv_org_abs_2309_17336
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation
Deng, Jianning
Chan, Gabriel
Zhong, Hantao
Lu, Chris Xiaoxuan
Computer Vision and Pattern Recognition
Robotics
This paper presents a novel framework for robust 3D object detection from point clouds via cross-modal hallucination. Our proposed approach is agnostic to either hallucination direction between LiDAR and 4D radar. We introduce multiple alignments on both spatial and feature levels to achieve simultaneous backbone refinement and hallucination generation. Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar. The feature alignment step further bridges the intrinsic attribute gap between the sensing modalities and stabilizes the training. The trained object detection models can deal with difficult detection cases better, even though only single-modal data is used as the input during the inference stage. Extensive experiments on the View-of-Delft (VoD) dataset show that our proposed method outperforms the state-of-the-art (SOTA) methods for both radar and LiDAR object detection while maintaining competitive efficiency in runtime. Code is available at https://github.com/DJNing/See_beyond_seeing.
title Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2309.17336