Xin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xin Li has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Angfan Zhu
School of Artificial Intelligence and Automation National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology 430074 Wuhan China
1 shared publication Chen Zhao
School of Artificial Intelligence and Automation National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology 430074 Wuhan China
1 shared publication- Jiaqi Yang
Northwestern Polytechnical University
1 shared publication - Xin Xiong
School of Artificial Intelligence and Automation National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology 430074 Wuhan China
1 shared publication - Zhiguo Cao
Huazhong University of Science and Technology, Wuhan, China
1 shared publication
Latest Publications
- Open Access
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS.
Open AccessRotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS.