AI Paper Atlas

Research map / 3D vision / Human pose estimation

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks

N. Dinesh Reddy, Minh Vo, Srinivasa G. Narasimhan

CVPR 2019 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 80 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypoints, TruncationPCK@0.1: 78.5 -> 87.41Improved
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypoints, Oth-OccPCK@0.1: 85.3 -> 86.45Improved
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypoints, Car-OccPCK@0.1: 82.9 -> 81.68Hurt
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypoints, AllPCK@0.1: 85.0 -> 88.8Improved
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypoints, 3D Full3D keypoint localization: 95.3 -> 93.2Hurt
Use Occlusion-Net instead of [25]KITTI-3D visible keypoints · KITTI-3D visible keypointsyaw error: 2.2 -> 1.9Improved
Add a graph encoder for occlusion prediction (ablation)MaskRCNN keypoint detector · CarFusion occlusion predictionAUC: 0.83 -> 0.95Improved
Add graph-based keypoint localization (ablation)MaskRCNN · Car-render, 3 invisible pointsPCK: 22%Improved
Add graph-based keypoint localization (ablation)MaskRCNN · Car-render, 9 invisible pointsPCK: 10%Improved
Add graph-based keypoint localization (ablation)MaskRCNN · CarFusion, 3 occluded pointsPCK: 6%Improved
Add graph-based keypoint localization (ablation)MaskRCNN · CarFusion, severe occlusionPCK: 10% or moreImproved
Add 3D-KGNN instead of relying only on 2D-KGNN (ablation)Occlusion-Net · Car-render, varying number of invisible pointsPCK: variance of 5%; 15%; 25%Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy