HyperAIHyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

6D Pose Estimation Using Rgb On Occlusion

評価指標

Mean ADD

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Mean ADD
Paper TitleRepository
ROPE45.95Occlusion-Robust Object Pose Estimation with Holistic Representation-
CullNet24.48CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation-
E2E6DoF47.4End-to-End Differentiable 6DoF Object Pose Estimation with Local and Global Constraints-
DPOD47.25DPOD: 6D Pose Object Detector and Refiner-
HybridPose47.5HybridPose: 6D Object Pose Estimation under Hybrid Representations-
SegDriven27Segmentation-driven 6D Object Pose Estimation-
PVNet40.77PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation-
RePOSE51.6RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering-
RNNPose (Trained with synthetic data and LINEMOD training set, w/o pbr data)60.65RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization-
GDR-Net56.1GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator-
DeepIM (Train on Occlusion LineMOD)55.5DeepIM: Deep Iterative Matching for 6D Pose Estimation-
PPC (Refined from initial PVNet pose)55.33Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors-
SO-Pose62.3SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation-
0 of 13 row(s) selected.
6D Pose Estimation Using Rgb On Occlusion | SOTA | HyperAI超神経