no code implementations • 31 Mar 2023 • Chenghao Shi, Xieyuanli Chen, Huimin Lu, Wenbang Deng, Junhao Xiao, Bin Dai
The proposed 3D-RoFormer fuses 3D position information into the transformer network, efficiently exploiting point clouds' contextual and geometric information to generate robust superpoint correspondences.
1 code implementation • 8 Mar 2023 • Wenbang Deng, Kaihong Huang, Qinghua Yu, Huimin Lu, Zhiqiang Zheng, Xieyuanli Chen
In this paper, we present a flexible and effective OIS framework for LiDAR point cloud that can accurately segment both known and unknown instances (i. e., seen and unseen instance categories during training).