Search Results for author: Rui Wan

Found 5 papers, 0 papers with code

Generalized Graph Embedding Models

no code implementations ICLR 2018 Qiao Liu, Xiao-Hui Yang, Rui Wan, Shouzhong Tu, Zufeng Wu

Many types of relations in physical, biological, social and information systems can be modeled as homogeneous or heterogeneous concept graphs.

General Classification Graph Embedding +2

DRINet++: Efficient Voxel-as-point Point Cloud Segmentation

no code implementations16 Nov 2021 Maosheng Ye, Rui Wan, Shuangjie Xu, Tongyi Cao, Qifeng Chen

The Sparse Feature Encoder extracts the local context information for each point, and the Sparse Geometry Feature Enhancement enhances the geometric properties of a sparse point cloud via multi-scale sparse projection and attentive multi-scale fusion.

Point Cloud Segmentation Segmentation +1

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

no code implementations16 Jan 2022 Shuangjie Xu, Rui Wan, Maosheng Ye, Xiaoyi Zou, Tongyi Cao

Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to separate each other.

Panoptic Segmentation

From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion

no code implementations25 Sep 2022 Rui Wan, Shuangjie Xu, Wei Wu, Xiaoyi Zou, Tongyi Cao

The whole fusion architecture named Dynamic Cross Attention Network (DCAN) exploits multi-level image features and adapts to multiple representations of point clouds, which allows DCA to serve as a plug-in fusion module.

Autonomous Driving

PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection

no code implementations18 Jan 2023 Rui Wan, Tianyun Zhao, Wei Zhao

However, due to the intrinsic discrepancies between the LiDAR point and camera image, the fusion of the data for object detection encounters a series of problems.

3D Object Detection Autonomous Driving +2

Cannot find the paper you are looking for? You can Submit a new open access paper.