DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection

Yao Rong, Xiangyu Wei, Tianwei Lin, Yueyu Wang, Enkelejda Kasneci

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

7 Zitate (Scopus)

Abstract

Augmenting LiDAR input with multiple previous frames provides richer semantic information and thus boosts performance in 3D object detection, However, crowded point clouds in multi-frames can hurt the precise position information due to the motion blur and inaccurate point projection. In this work, we propose a novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single-frame (static branch). To effectively extract and aggregate complimentary features, DynStaF contains two modules, Neighborhood Cross Attention (NCA) and Dynamic-Static Interaction (DSI), operating through a dual pathway architecture. NCA takes the features in the static branch as queries and the features in the dynamic branch as keys (values). When computing the attention, we address the sparsity of point clouds and take only neighborhood positions into consideration. NCA fuses two features at different feature map scales, followed by DSI providing the comprehensive interaction. To analyze our proposed strategy DynStaF, we conduct extensive experiments on the nuScenes dataset. On the test set, DynStaF increases the performance of PointPillars in NDS by a large margin from 57.7% to 61.6%. When combined with CenterPoint, our framework achieves 61.0% mAP and 67.7% NDS, leading to the state-of-the-art performance without bells and whistles. Our Code will be publicly available.

OriginalspracheEnglisch
TitelProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Herausgeber (Verlag)IEEE Computer Society
Seiten3238-3247
Seitenumfang10
ISBN (elektronisch)9798350302493
DOIs
PublikationsstatusVeröffentlicht - 2023
Extern publiziertJa
Veranstaltung2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Kanada
Dauer: 18 Juni 202322 Juni 2023

Publikationsreihe

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Band2023-June
ISSN (Print)2160-7508
ISSN (elektronisch)2160-7516

Konferenz

Konferenz2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Land/GebietKanada
OrtVancouver
Zeitraum18/06/2322/06/23

Fingerprint

Untersuchen Sie die Forschungsthemen von „DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren