ApolloCar3D

Introduced by Song et al. in ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

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

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Car Pose Estimation	ApolloCar3D	Zauss et al.
3D Car Instance Understanding	ApolloCar3D	BAAM
Autonomous Vehicles	ApolloCar3D	BAAM
3D Shape Reconstruction	ApolloCar3D	GSNet
Vehicle Key-Point and Orientation Estimation	ApolloCar3D	GSNet
Pose Estimation	ApolloCar3D	GSNet
6D Pose Estimation	ApolloCar3D	GSNet
3D Pose Estimation	ApolloCar3D	GSNet
3D Reconstruction	ApolloCar3D	GSNet
3D Shape Reconstruction From A Single 2D Image	ApolloCar3D	GSNet
Autonomous Driving	ApolloCar3D	GSNet
Keypoint Detection	ApolloCar3D	GSNet
6D Pose Estimation using RGB	ApolloCar3D	GSNet
Vehicle Pose Estimation	ApolloCar3D	GSNet