Xiaoxiao Geng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoxiao Geng has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Lingli Zhao
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
1 shared publication - Meng Lu
Department of Geography, University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, Germany
1 shared publication - Shunping Ji
Wuhan University
1 shared publication
Latest Publications
- Open Access
- 14 February 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (4) , 691
Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation
Semantic segmentation of LiDAR point clouds has implications in self-driving, robots, and augmented reality, among others. In this paper, we propose a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance. First, upon a baseline encoder-decoder architecture for point cloud segmentation, namely, RandLA-Net, an attentive skip connection was proposed to replace the commonly used concatenation to balance the encoder and decoder features of the same scales. Second, a channel attentive enhancement module was introduced to the local attention enhancement module to boost the local feature discriminability and aggregate the local channel structure information. Third, we developed a multi-scale feature aggregation method to capture the global structure of a point cloud from both the encoder and the decoder. The experimental results reported that our MSAAN significantly outperformed state-of-the-art methods, i.e., at least 15.3% mIoU improvement for scene-2 of CSPC dataset, 5.2% for scene-5 of CSPC dataset, and 6.6% for Toronto3D dataset.
- 14 February 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (4) , 691
Open AccessMulti-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation
Semantic segmentation of LiDAR point clouds has implications in self-driving, robots, and augmented reality, among others. In this paper, we propose a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance. First, upon a baseline encoder-decoder architecture for point cloud segmentation, namely, RandLA-Net, an attentive skip connection was proposed to replace the commonly used concatenation to balance the encoder and decoder features of the same scales. Second, a channel attentive enhancement module was introduced to the local attention enhancement module to boost the local feature discriminability and aggregate the local channel structure information. Third, we developed a multi-scale feature aggregation method to capture the global structure of a point cloud from both the encoder and the decoder. The experimental results reported that our MSAAN significantly outperformed state-of-the-art methods, i.e., at least 15.3% mIoU improvement for scene-2 of CSPC dataset, 5.2% for scene-5 of CSPC dataset, and 6.6% for Toronto3D dataset.