no code implementations • 7 May 2024 • Chen Min, Dawei Zhao, Liang Xiao, Jian Zhao, Xinli Xu, Zheng Zhu, Lei Jin, Jianshu Li, Yulan Guo, Junliang Xing, Liping Jing, Yiming Nie, Bin Dai
In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal fashion.
2 code implementations • 10 Apr 2024 • Hao Lu, Jiaqi Tang, Xinli Xu, Xu Cao, Yunpeng Zhang, Guoqing Wang, Dalong Du, Hao Chen, Yingcong Chen
Finally, for MC3D-Det joint training, the elaborate dataset merge strategy is designed to solve the problem of inconsistent camera numbers and camera parameters.
1 code implementation • ICCV 2023 • Jie Wang, Lihe Ding, Tingfa Xu, Shaocong Dong, Xinli Xu, Long Bai, Jianan Li
Robust 3D perception under corruption has become an essential task for the realm of 3D vision.
1 code implementation • 28 Dec 2022 • Peixiang Huang, Li Liu, Renrui Zhang, Song Zhang, Xinli Xu, Baichao Wang, Guoyi Liu
In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.
no code implementations • 22 Sep 2022 • Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li
Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement.
2 code implementations • 20 Jun 2022 • Chen Min, Xinli Xu, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai
This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE).