Waymo Open Dataset Challenge Reports
3D Detection
Given one or more lidar range images and the associated camera images, produce a set of 3D upright boxes for the objects in the scene. This is a simplified version of the 3D tracking challenge in that it ignores the temporal component. A baseline open source model is linked below for your reference.
1st place
Zhuangzhuang Ding, Yihan Hu, Runzhou Ge, Li Huang, Sijia Chen, Yu Wang and Jie Liao
Team Horizon
2nd place
Shaoshuai Shi, Chaoxu Guo, Jihan Yang and Hongsheng Li
The Chinese University of Hong Kong, The University of Hong Kong
3rd place
Feng Wang, Zhichao Li, Yan Yan and Naiyan Wang
Team TuSimple
3D Tracking
Given a temporal sequence (prior frames) of lidar and camera data, produce a set of 3D upright boxes and the correspondences between boxes across frames. (Entries that use future frames will be ineligible for awards.) You may use the baseline model or object detections linked below, if you wish.
1st place
Zhuangzhuang Ding, Yihan Hu, Runzhou Ge, Li Huang, Sijia Chen, Yu Wang and Jie Liao
Team Horizon
2nd place
Shaoshuai Shi, Chaoxu Guo, Jihan Yang and Hongsheng Li
The Chinese University of Hong Kong, The University of Hong Kong
3rd place
Almaz Zinollayev
BTSDigital
2D Detection
Given a set of camera images, produce a set of 2D boxes for the objects in the scene.
1st place
Zehao Huangj, Zehui Chen, Qiaofei Li, Hongkai Zhang and Naiyan Wang
Team TuSimple, Tongji University, Xidian University, Chinese Academy of Sciences
2nd place
Sijia Chen, Yu Wang, Li Huang, Runzhou Ge, Yihan Hu, Zhuangzhuang Ding and Jie Liao
Team Horizon
3rd place
Hang Xu, Chenhan Jiang, Dapeng Feng, Chaoqiang Ye, Rui Sun and Xiaodan Liang
Sun Yat-Sen University
2D Tracking
Given a temporal sequence (prior frames) of camera images, produce a set of 2D boxes and the correspondences between boxes across frames. (Entries that use future frames will be ineligible for awards.) You may use the baseline object detections linked below, if you wish.
1st place
Zhuangzhuang Ding, Yihan Hu, Runzhou Ge, Li Huang, Sijia Chen, Yu Wang and Jie Liao
Team Horizon
2nd place
Jiangmiao Pang, Linlu Qiu, Haofeng Chen and Fisher Yu
UC Berkeley
3rd place
Yuan Xu and Erdene-Ochir Tuguldur
Technische Universität Berlin
domain adaptation
Similar to the 3D Detection Challenge: given one or more range images and the associated camera images, produce a set of 3D upright boxes for the objects in the scene. However, we provide additional segments from a new location and only a subset have labels.
1st place
Zhuangzhuang Ding, Yihan Hu, Runzhou Ge, Li Huang, Sijia Chen, Yu Wang and Jie Liao
Team Horizon
2nd place
Shaoshuai Shi, Chaoxu Guo, Jihan Yang and Hongsheng Li
The Chinese University of Hong Kong, The University of Hong Kong
3rd place
Cunjun Yu, Zhongang Cai, Daxuan Ren and Haiyu Zhao
Innova