1 code implementation • 27 Jun 2023 • Peng Xu, Zhiyu Xiang, Chenyu Qiao, Jingyun Fu, Tianyu Pu
Existing works simply assume that the ground-truth distributions are uni-modal, which ignores the fact that most of the edge pixels can be multi-modal.
no code implementations • 7 Jul 2022 • Qihao Peng, Zhiyu Xiang, YuanGang Fan, Tengqi Zhao, Xijun Zhao
As a fundamental task for intelligent robots, visual SLAM has made great progress over the past decades.
no code implementations • 26 May 2022 • Chengyu Qiao, Zhiyu Xiang, Xinglu Wang
Visual relocalization aims to estimate the pose of a camera from one or more images.
1 code implementation • CVPR 2022 • Jiaqi Gu, Bojian Wu, Lubin Fan, Jianqiang Huang, Shen Cao, Zhiyu Xiang, Xian-Sheng Hua
Monocular 3D object detection is an essential task in autonomous driving.
no code implementations • 13 Mar 2022 • Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang
In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies.
no code implementations • 28 Aug 2021 • Jiaqi Gu, Zhiyu Xiang, Yuwen Ye, Lingxuan Wang
Depth Completion can produce a dense depth map from a sparse input and provide a more complete 3D description of the environment.
1 code implementation • ICCV 2021 • Wentao Du, Zhiyu Xiang, Shuya Chen, Chengyu Qiao, Yiman Chen, Tingming Bai
Although instance segmentation has made considerable advancement over recent years, it's still a challenge to design high accuracy algorithms with real-time performance.