Zixiang Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zixiang Zhou has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hassan Foroosh
University of Central Florida
2 shared publications - Boqing Gong
Boston University
1 shared publication - Panqu Wang
TuSimple, Inc
1 shared publication - Philip David
Computational and Information Sciences Directorate U.S. Army Research Laboratory
1 shared publication - Xiangchen Zhao
TuSimple
1 shared publication - Xiangyu Yue
The Chinese University of Hong Kong
1 shared publication
Latest Publications
- Top Cited Papers
- 23 October 2022
- Published by Springer Nature
- p. 496-513
CenterFormer: Center-Based Transformer for 3D Object Detection
- 23 October 2022
- Published by Springer Nature
- p. 496-513
Top Cited PapersCenterFormer: Center-Based Transformer for 3D Object Detection
- Open Access
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR. Despite the emerging datasets and technological advancements, it remains challenging due to three reasons: (1) the need for near-real-time latency with limited hardware; (2) uneven or even long-tailed distribution of LiDAR points across space; and (3) an increasing number of extremely fine-grained semantic classes. In an attempt to jointly tackle all the aforementioned challenges, we propose a new LiDAR-specific, nearest-neighbor-free segmentation algorithm - PolarNet. Instead of using common spherical or bird's-eye-view projection, our polar bird's-eye-view representation balances the points across grid cells in a polar coordinate system, indirectly aligning a segmentation network's attention with the long-tailed distribution of the points along the radial axis. We find that our encoding scheme greatly increases the mIoU in three drastically different segmentation datasets of real urban LiDAR single scans while retaining near real-time throughput.
Open AccessPolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR. Despite the emerging datasets and technological advancements, it remains challenging due to three reasons: (1) the need for near-real-time latency with limited hardware; (2) uneven or even long-tailed distribution of LiDAR points across space; and (3) an increasing number of extremely fine-grained semantic classes. In an attempt to jointly tackle all the aforementioned challenges, we propose a new LiDAR-specific, nearest-neighbor-free segmentation algorithm - PolarNet. Instead of using common spherical or bird's-eye-view projection, our polar bird's-eye-view representation balances the points across grid cells in a polar coordinate system, indirectly aligning a segmentation network's attention with the long-tailed distribution of the points along the radial axis. We find that our encoding scheme greatly increases the mIoU in three drastically different segmentation datasets of real urban LiDAR single scans while retaining near real-time throughput.