Roadside Perception 3D (Rope3D) is a dataset for autonomous driving and monocular 3D object detection task consisting of 50k images and over 1.5M 3D objects in various scenes, which are captured under different settings including various cameras with ambiguous mounting positions, camera specifications, viewpoints, and different environmental conditions.
Variants: Rope3D
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 3D Object Detection | CoBEV | CoBEV: Elevating Roadside 3D Object … | 2023-10-04 |
| 3D Object Detection | BEVHeight | BEVHeight: A Robust Framework for … | 2023-03-15 |
| 3D Object Detection | BEVFormer | BEVFormer v2: Adapting Modern Image … | 2022-11-18 |
| 3D Object Detection | BEVDepth | BEVDepth: Acquisition of Reliable Depth … | 2022-06-21 |
| 3D Object Detection | MonoDLE+(G) | Delving into Localization Errors for … | 2021-03-30 |
| 3D Object Detection | Kinematic3D+(G) | Kinematic 3D Object Detection in … | 2020-07-19 |
| 3D Object Detection | M3D-RPN+(G) | M3D-RPN: Monocular 3D Region Proposal … | 2019-07-13 |
Recent papers with results on this dataset: