Dense semantic scene understanding of the surrounding environment in top-view is a crucial task for autonomous vehicles. Recent LiDAR-based semantic perception works mainly focus on point-wise predictions of the LiDAR points instead of dense predictions of the environment, making them not appropriate for path-planning tasks. Pillar and voxel representations can achieve dense predictions, but the generation of data representation and data processing are usually time-consuming. In this article, we propose a top-view semantic completion network to produce accurate dense grid-wise predictions with real-time performance. Specifically, we propose an online distillation strategy, consisting of two parts: a student model using 2D range-view and top-view representations, and a teacher model using range-view, top-view, and voxel representations. To realize information transfer between different representations, we propose a cross-view association (CVA) module, by which the range-view features and 3D voxel features are converted into the ones in the top-view. The proposed method can avoid the difficulty of direct dense semantic segmentation in the top-view, with the point-wise sparse semantic segmentation module acting as a guide for the dense grid-wise semantic completion in a semantic-completion way. It can also alleviate the computational complexity by using only the voxel representation and 3D convolution in the teacher model. The experimental results on the SemanticKITTI dataset (46.4% mIoU) and nuScenes-LidarSeg dataset (47.3% mIoU) demonstrate the effectiveness of the proposed sparse guidance and online distillation strategies.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Dense Top-View Semantic Completion With Sparse Guidance and Online Distillation


    Beteiligte:
    Gu, Shuo (Autor:in) / Lu, Jiacheng (Autor:in) / Yang, Jian (Autor:in) / Xu, Cheng-Zhong (Autor:in) / Kong, Hui (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2024-01-01


    Format / Umfang :

    3645446 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SPARSE VOXEL TRANSFORMER FOR CAMERA-BASED 3D SEMANTIC SCENE COMPLETION

    LI YIMING / YU ZHIDING / CHOY CHRISTOPHER B et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Dense-sparse discretization for optimization and real-time guidance

    Kumar, Renjith R. / Seywald, Hans | AIAA | 1996


    Image tag completion via dual-view linear sparse reconstructions

    Lin, Z. / Ding, G. / Hu, M. et al. | British Library Online Contents | 2014


    Dense context distillation network for semantic parsing of oblique UAV images

    Youli Ding / Xianwei Zheng / Yiping Chen et al. | DOAJ | 2022

    Freier Zugriff