PTv3-EX
| Authors | Xiaoyang Wu, Xiang Xu, Lingdong Kong, Liang Pan, Ziwei Liu, Tong He, Wanli Ouyang, Hengshuang Zhao |
| Description | This submission is majorly based on the paper " Point Transformer V3: Simpler, Faster, Stronger", which is accepted by CVPR 2024 as an Oral presentation. Specifically for this Waymo challenge, the Pointcept team further enhanced the performance with additional past and future frames as references. The training parameter is further tuned and optimized for data imbalance. |