activity
20172021
most citedA Surface Geometry Model for LiDAR Depth Completion

41 citations · 66 across the 14 of their papers we have counts for

collaborators

22 papers

cs.CV20212 cited

A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation

Yiming Zhao, Xiao Zhang, Xinming Huang

Clustering objects from the LiDAR point cloud is an important research problem with many applications such as autonomous driving. To meet the real-time requirement, existing resear…

cs.CV2021

FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

Yiming Zhao, Lin Bai, Xinming Huang

Projecting the point cloud on the 2D spherical range image transforms the LiDAR semantic segmentation to a 2D segmentation task on the range image. However, the LiDAR range image i…

cs.CV20213 cited

A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation

Yiming Zhao, Xiao Zhang, Xinming Huang

LiDAR panoptic segmentation is a newly proposed technical task for autonomous driving. In contrast to popular end-to-end deep learning solutions, we propose a hybrid method with an…

cs.CV20218 cited

Revisiting 2D Convolutional Neural Networks for Graph-based Applications

Yecheng Lyu, Xinming Huang, Ziming Zhang

Graph convolutional networks (GCNs) are widely used in graph-based applications such as graph classification and segmentation. However, current GCNs have limitations on implementat…

cs.CV20211 cited

Deep Lucas-Kanade Homography for Multimodal Image Alignment

Yiming Zhao, Xinming Huang, Ziming Zhang

Estimating homography to align image pairs captured by different sensors or image pairs with large appearance changes is an important and general challenge for many computer vision…

cs.CV202141 cited

A Surface Geometry Model for LiDAR Depth Completion

Yiming Zhao, Lin Bai, Ziming Zhang +1

LiDAR depth completion is a task that predicts depth values for every pixel on the corresponding camera frame, although only sparse LiDAR points are available. Most of the existing…