Monocular 3D object detection remains a challenging task due to the inherent limitations of single-view depth perception. While conventional methods treat all parts of the Region of Interest (RoI) uniformly, we argue that different RoI regions hold varying importance for accurate detection. This study introduces the Multi-Scale Grid Attention (MSGA) mechanism to investigate the significance of RoI regions at multiple scales. Furthermore, we propose a novel probabilistic post-processing method to enhance detection robustness by effectively utilizing the probabilistic properties of depth estimation during inference. Our approach achieves state-of-the-art performance on the KITTI and Waymo datasets, demonstrating significant improvements in detection accuracy and robustness.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Scale Grid Attention and Probabilistic Refinement for Accurate RoI-Based Monocular 3D Object Detection


    Contributors:
    Zhang, Tingyu (author) / Yang, Xinyu (author) / Liang, Zhigang (author) / Yang, Yanzhao (author) / Wang, Jian (author)


    Publication date :

    2025-06-01


    Size :

    2917902 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Attention-based Proposals Refinement for 3D Object Detection

    Dao, Minh-Quan / Hery, Elwan / Fremont, Vincent | IEEE | 2022


    Mono-DCNet: Monocular 3D Object Detection via Depth-based Centroid Refinement and Pose Estimation

    Astudillo, Armando / Al-Kaff, Abdulla / Garcia, Fernando | IEEE | 2022


    Multi-scale object detection based on attention mechanism

    Sun, Shenshen / Bao, Xue / Wang, Xirui | SPIE | 2024


    Change detection by probabilistic segmentation from monocular view

    Hernandez-Lopez, F. J. / Rivera, M. | British Library Online Contents | 2014


    RefineNet: Iterative refinement for accurate object localization

    Rajaram, Rakesh N. / Ohn-Bar, Eshed / Trivedi, Mohan M. | IEEE | 2016