HyperAI초신경

6D Pose Estimation Using Rgbd On Real275

평가 지표

mAP 10, 2cm

mAP 10, 5cm

mAP 3DIou@50

mAP 3DIou@75

mAP 5, 2cm

mAP 5, 5cm

평가 결과

이 벤치마크에서 각 모델의 성능 결과

							Paper Title
BundleTrack	-	-	-	-	-	87.4	BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
GenPose https://github.com/Jiyao06/GenPose	72.4	84.0	-	-	52.1	60.9	GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
gcasp	64.2	76.3	79.0	65.3	46.9	54.7	Generative Category-Level Shape and Pose Estimation with Semantic Primitives
GPV-Pose	-	73.3	83	64.4	32	42.9	GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
DualPoseNet	50	66.8	79.8	-	-	35.9	DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency
UDA-COPE	56.9	66.0	82.6	62.5	30.4	34.8	UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
6-PACK	-	-	-	-	-	33.3	6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
CenterSnap	-	64.3	80.2	-	-	29.1	CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation
FS-Net	-	60.8	92.2	63.5	-	28.2	FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
CPPF	-	44.9	26.4	-	-	16.9	CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild
NOCS (128 bins)	-	26.7	80.5	-	-	9.5	Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

0 of 11 row(s) selected.

6D Pose Estimation Using Rgbd On Real275 | SOTA | HyperAI초신경