Vehicle Pose Estimation On Kitti Cars Hard

Métriques

Average Orientation Similarity

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Ego-Net (Monocular RGB only)	80.96	Exploring intermediate representation for monocular vehicle pose estimation
Deep-Manta	80.39	Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image
3D R-CNN	80.07	3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
SubCNN	78.68	Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
DSGN (Stereo)	78.27	DSGN: Deep Stereo Geometry Network for 3D Object Detection
RTM-3D	77.18	RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
FQNet	76.85	Deep Fitting Degree Scoring Network for Monocular 3D Object Detection
Mono3D	76.84	Monocular 3D Object Detection for Autonomous Driving
Deep3DBoX	76.76	3D Bounding Box Estimation Using Deep Learning and Geometry
3DOP	76.52	3D Object Proposals for Accurate Object Class Detection
MonoPair	76.45	MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
ML-Fusion	76.37	Multi-Level Fusion Based 3D Object Detection From Monocular Images
MonoPSR	72.26	Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
Disp-RCNN (Stereo)	67.16	Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
M3D-RPN	67.08	M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
RAR-Net	66.90	Reinforced Axial Refinement Network for Monocular 3D Object Detection
D4LCN	63.98	Learning Depth-Guided Convolutions for Monocular 3D Object Detection
GS3D	61.85	GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
Kinematic3D	34.81	Kinematic 3D Object Detection in Monocular Video

0 of 19 row(s) selected.

Vehicle Pose Estimation On Kitti Cars Hard | SOTA | HyperAI