139 citations · 358 across the 13 of their papers we have counts for
14 papers · 1 filter
ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
Xiangze Jia, Hui Zhou, Xinge Zhu +3
In this paper, we propose a novel self-supervised motion estimator for LiDAR-based autonomous driving via BEV representation. Different from usually adopted self-supervised strateg…
LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network
Fangzhou Hong, Hui Zhou, Xinge Zhu +2
With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the…
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Xiao Song, Guorun Yang, Xinge Zhu +4
Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited…
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
Xinge Zhu, Hui Zhou, Tai Wang +6
State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the poin…
LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation
Lin Zhao, Hui Zhou, Xinge Zhu +3
Camera and 3D LiDAR sensors have become indispensable devices in modern autonomous driving vehicles, where the camera provides the fine-grained texture, color information in 2D spa…
LiDAR-based Panoptic Segmentation via Dynamic Shifting Network
Fangzhou Hong, Hui Zhou, Xinge Zhu +2
With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the…
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Xinge Zhu, Hui Zhou, Tai Wang +5
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corpora…
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
Hui Zhou, Xinge Zhu, Xiao Song +4
State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spher…
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Xiao Song, Guorun Yang, Xinge Zhu +3
Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite poor. A…
SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud
Hongwei Yi, Shaoshuai Shi, Mingyu Ding +6
3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two as…
Robust Multi-Modality Multi-Object Tracking
Wenwei Zhang, Hui Zhou, Shuyang Sun +3
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential moveme…
Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
Xinge Zhu, Hui Zhou, Ceyuan Yang +2
Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance o…
Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
Hui Zhou, Wanli Ouyang, Jian Cheng +2
Online Multi-Object Tracking (MOT) is a challenging problem and has many important applications including intelligence surveillance, robot navigation and autonomous driving. In exi…
Crafting GBD-Net for Object Detection
Xingyu Zeng, Wanli Ouyang, Junjie Yan +9
The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of loca…