This paper proposes an innovative approach using attention mechanisms and semantic refinement to enhance feature representation and alleviate the strong dependency between semantic prediction and instance segmentation, providing a novel technical pathway for point cloud instance segmentation.
The complex spatial structures and varying scales of point cloud data make semantic segmentation a highly challenging task. While downsampling and feature fusion are essential steps in mainstream networks, existing models often suffer from local geometry loss and multiscale semantic conflicts during these processes. To...
GeoFuse-AL is proposed, a label-efficient segmentation framework that integrates a geometry-guided point–voxel network with multi-cue active learning and improves segmentation accuracy while substantially reducing annotation requirements.
SDA-Reg is introduced, a registration network based on semantically enhanced features and a dual-stream attention architecture that outperforms baseline methods by 1.43%, demonstrating robust accuracy in dynamic environments.
Sheng-Jie Fu, Qi-Peng Cai, Zhao-Yuan Yao et al.· Scientific Reports· 0 citations
Three-dimensional object detection is a key component of the perception module in autonomous driving systems. Compared to camera images, LiDAR point clouds provide richer spatial information, such as detailed structural and geometric cues of objects. However, existing 3D object detection methods face two major challeng...
Xiangyang Wu, Ji-Tao Pan, Qing-Long Jiao et al.· IEEE transactions on intelli...· 0 citations
A complementary prototype representation framework is proposed, employing three modules to collaboratively improve pseudo-label quality and improves the discriminative ability of confused categories by generating semantically similar sub-category negative samples.
