MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues

3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset. Code is available at code and video.

Authors

• Zhaofeng Hu
• Sifan Zhou
• Zhihang Yuan
• Dawei Yang
• Shibo Zhao
• Ci-Jyun Liang

Keywords

• Point cloud compression
• Three-dimensional displays
• Codes
• Object segmentation
• Performance gain
• Sensor systems
• Sensors
• Object tracking
• Robots
• Videos
• Point Cloud
• Virtual Cues
• Single Tracking
• Seamless Integration
• 3D Tracking
• Sparse Point Cloud
• Pedestrian
• 2D Images
• 3D Space
• Bounding Box
• RGB Images
• Small Objects
• Tracking Performance
• 3D Coordinates
• Tracking Task
• RGB Camera
• Siamese Network
• Raw Point
• Motion Compensation
• LiDAR Point
• 3D Bounding Box
• LiDAR Point Clouds
• 2D Image Plane
• Virtual Point
• 2D Object
• Motion Cues
• Semantic
• Object Distance
• Geometric Information
• Object Detection