2021/03/30 by Zetong Yang, Yang, Zetong, Yin Zhou +5 · 4 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Aggregate (composite) #Artificial intelligence #Computer science #Computer vision #Detector #Feature (linguistics) #Focus (optics) #Frame (networking) #Frame rate #Object (grammar) #Object detection #Pattern recognition (psychology) #Robotics and Sensor-Based Localization #State (computer science) #Telecommunications #Visual Attention and Saliency Detection #cs.CV
paper · pdf · doi:10.48550/arxiv.2103.16054
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/03/30 · openalex publication_date 2021/03/30 · arxiv updated 2021/03/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
3D object detection is an important module in autonomous driving and robotics. However, many existing methods focus on using single frames to perform 3D detection, and do not fully utilize information from multiple frames. In this paper, we present 3D-MAN: a 3D multi-frame attention network that effectively aggregates features from multiple perspectives and achieves state-of-the-art performance on Waymo Open Dataset. 3D-MAN first uses a novel fast single-frame detector to produce box proposals. The box proposals and their corresponding feature maps are then stored in a memory bank. We design a multi-view alignment and aggregation module, using attention networks, to extract and aggregate the temporal features stored in the memory bank. This effectively combines the features coming from different perspectives of the scene. We demonstrate the effectiveness of our approach on the large-scale complex Waymo Open Dataset, achieving state-of-the-art results compared to published single-frame and multi-frame methods.