Monocular 3D Object Detection on Google Objectron

18개 결과 · ⬇ CSV · JSON

Average Precision at 0.5 3D IoU

Rank	Model	Average Precision at 0.5 3D IoU	MPE	AP at 15' Azimuth error	AP at 10' Elevation error	Paper	Code	Year
1	Lin2021	0.7218	0.0520	0.8398	0.8560
2	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
3	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020
4	Lin2021	0.7218	0.0520	0.8398	0.8560
5	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
6	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020
7	Lin2021	0.7218	0.0520	0.8398	0.8560
8	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
9	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020
10	Lin2021	0.7218	0.0520	0.8398	0.8560
11	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
12	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020
13	Lin2021	0.7218	0.0520	0.8398	0.8560
14	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
15	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020
16	Lin2021	0.7218	0.0520	0.8398	0.8560
17	EfficientNetLite + keypoint regressor	0.6512	0.0467	0.7844	0.8584	Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	google-research-datasets/Objectron	2020
18	MobilePose	0.4624	0.1001	0.5088	0.6658	MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision		2020