ApolloCar3DT is a dataset that contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20 times larger than PASCAL3D+ and KITTI, the current state-of-the-art.
Source: ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Image Source: http://apolloscape.auto/car_instance.html
Variants: ApolloCar3D
This dataset is used in 9 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Autonomous Vehicles | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| 3D Reconstruction | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| Pose Estimation | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| Autonomous Driving | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| Vehicle Key-Point and Orientation Estimation | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| 3D Shape Reconstruction From A Single 2D Image | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| 3D Shape Reconstruction | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| 6D Pose Estimation | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
| 3D Pose Estimation | GSNet | GSNet: Joint Vehicle Pose and … | 2020-07-26 |
Recent papers with results on this dataset: