Robust 3D Shape Classification via Non-Local Graph Attention Network

no code implementations • CVPR 2023 • Shengwei Qin, Zhong Li, Ligang Liu

Especially, in the case of sparse point clouds (64 points) with noise under arbitrary SO(3) rotation, the classification result (85. 4%) of NLGAT is improved by 39. 4% compared with the best development of other methods.

3D Shape Classification Classification +2