How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
:fire: Visual point cloud forecasting, a new self-supervised pre-training task for end-to-end autonomous driving, predicting future point clouds from historical visual inputs, joint modeling the 3D geometry and temporal dynamics for simultaneous perception, prediction, and planning.
The main features of opendrivelab/vidar are: Driving World Models.
Projects with overlapping indexed features include: 6550zhao/policy-world-model — Zhida Zhao¹· Talas Fu¹ · Yifan Wang¹ · Lijun Wang¹† · Huchuan Lu¹. antonioo-c/geodrive — GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control. bravegroup/drive-wm — Yuqi Wang, Jiawei He, Lue Fan, Hongxin Li, Yuntao Chen†, Zhaoxiang Zhang† (*: Equal Contribution; †: Corresponding… bravegroup/law — Yingyan Li, Lue Fan, Jiawei He, Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang and Tieniu Tan. chaytonmin/orad-3d. 3dtopia/dynamiccity — Hengwei Bian 1,2, Lingdong Kong 1,3 Haozhe Xie 4 Liang Pan…
Zhida Zhao¹· Talas Fu¹ · Yifan Wang¹ · Lijun Wang¹† · Huchuan Lu¹
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
Yuqi Wang, Jiawei He, Lue Fan, Hongxin Li, Yuntao Chen†, Zhaoxiang Zhang† (*: Equal Contribution; †: Corresponding Author)
Hengwei Bian 1,2, Lingdong Kong 1,3 Haozhe Xie 4 Liang Pan 1,†,‡ Yu Qiao 1 Ziwei Liu 4 1 Shanghai AI Laboratory 2 Carnegie Mellon University 3 National University of…