3D object detection based on multi-camera is essential for autonomous driving systems. The current popular multi-camera detectors can be decoupled into multiple feature extraction modules with different functions. Such network paradigms often lead to the pre-trained image backbone module only receiving implicit and sparse supervision signals, and the image depth estimation has inherent ambiguity, which collectively limits the performance of the detector. In this paper, we present DenseBEV, a robust solution to bird’s-eye-view (BEV) 3D object detection with densely aggregated multi-view camera features. Specifically, we propose a novel multiview multiscale cross-attention (MMCA) module in the BEV decoder, which makes the BEV object query interact with multi-camera features in a standard attention paradigm. The aim of the MMCA is to make the pre-trained image backbone more easily optimized for 3D scenes for autonomous driving. Furthermore, we introduce contrastive denoising in the decoder head to assist in training the BEV detection model, alleviating the chaotic prediction problem caused by indistinct image depth estimations. Our method achieves significant improvements (i.e., +2.3NDS and +2.8mAP) over previous state-of-the-art BEV-based methods on the challenging nuScenes validation set. DenseBEV also achieved competitive results of 63.1 NDS and 55.4 mAP on the nuScenes test set.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Denoising Transformer for BEV 3D Object Detection via Multiview Multiscale Cross-Attention


    Contributors:
    Zhao, Xiao (author) / Zhang, Xukun (author) / Chen, Guang (author) / Wei, Xiaoyi (author) / Li, Zhenpeng (author) / Xu, Zhi (author) / Wang, Youxing (author) / Zhu, Jingyi (author) / Zhai, Peng (author) / Zhang, Lihua (author)


    Publication date :

    2025-07-01


    Size :

    2082209 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Multiview feature distributions for object detection and continuous pose estimation

    Teney, D. / Piater, J. | British Library Online Contents | 2014


    CASwin Transformer: A Hierarchical Cross Attention Transformer for Depth Completion

    Feng, Chunyu / Wang, Xiaonian / Zhang, Yangyang et al. | IEEE | 2022



    Image Denoising using Multiscale Directional Cosine Bases

    Yao, Z. / Rajpoot, N. | British Library Conference Proceedings | 2005


    3-D multiview object representations for model-based object recognition

    Korn, Matthew R. / Dyer, Charles R. | TIBKAT | 1985