In this paper, we propose a point cloud based 3D object detection framework that accounts for both contextual and local information by leveraging multi-receptive field pillars, named as MuRF-Net. Recently, common pipelines can be divided into a voxel-based feature encoder and an object detector. During the feature encoding steps, contextual information is neglected, which is critical for the 3D object detection task. Thus, the encoded features are not suitable to input to the subsequent object detector. To address this challenge, we propose the MuRF-Net with a multi-receptive field voxelization mechanism to capture both contextual and local information. After the voxelization, the voxelized points (pillars) are processed by a feature encoder, and a channel-wise feature reconfiguration module is proposed to combine the features with different receptive fields using a lateral enhanced fusion network. In addition, to handle the increase of memory and computational cost brought by multi-receptive field voxelization, a dynamic voxel encoder is applied taking advantage of the sparseness of the point cloud. Experiments on the KITTI benchmark for both 3D object and Bird's Eye View (BEV) detection tasks on car class are conducted and MuRF-Net achieved the state-of-the-art results compared with other voxel-based methods. Besides, the MuRF-Net can achieve nearly real-time speed with 20Hz.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MuRF-Net: Multi-Receptive Field Pillars for 3D Object Detection from Point Cloud


    Contributors:
    Yang, Zhuo (author) / Huang, Yuhao (author) / Yan, Xinrui (author) / Chen, Shitao (author) / Dong, Jinpeng (author) / Sun, Jun (author) / Liu, Ziyi (author) / Nan, Zhixiong (author) / Zheng, Nanning (author)


    Publication date :

    2020-10-19


    Size :

    3161135 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hybrid receptive field network for small object detection on drone view

    CHEN, Zhaodong / JI, Hongbing / ZHANG, Yongquan et al. | Elsevier | 2025

    Free access

    Remote Sensing Image Object Detection Algorithm Based on Receptive Field Enhancement

    MingJun, Liu / Yun, Zhang / Rui, Zhang et al. | Springer Verlag | 2022


    Remote Sensing Image Object Detection Algorithm Based on Receptive Field Enhancement

    MingJun, Liu / Yun, Zhang / Rui, Zhang et al. | British Library Conference Proceedings | 2022


    Point Cloud Completion by Larger Receptive Fields for Intelligent Vehicles

    Zhang, Yunqing / Zhang, Xiaotong / Liu, Kunhua et al. | IEEE | 2023


    Multi‐receptive field graph convolutional neural networks for pedestrian detection

    Shen, Chao / Zhao, Xiangmo / Fan, Xing et al. | Wiley | 2019

    Free access