AI Paper Atlas

Research map / 3D vision / Human pose estimation

PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation

Sida Peng, Yuan Liu, Qixing Huang, Xiaowei Zhou, Hujun Bao

CVPR 2019 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 1,079 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
Replace direct keypoint-coordinate regression with pixel-wise voting (ablation)Keypoint-based pose estimation · Occlusion LINEMODADD(-S): 6.42 -> 33.88Improved
Select keypoints on the object surface using FPS rather than bounding-box corners (ablation)PVNet · Occlusion LINEMODADD(-S): 33.88 -> 39.76Improved
Increase the number of FPS surface keypoints from 4 to 8 (ablation)PVNet · Occlusion LINEMODADD(-S): 17.96 -> 39.76Improved
Increase the number of FPS surface keypoints from 8 to 12 (ablation)PVNet · Occlusion LINEMODADD(-S): 39.76 -> 39.92No clear effect
Use uncertainty-driven PnP instead of EPnP (ablation)PVNet with 8 FPS keypoints · Occlusion LINEMODADD(-S): 39.76 -> 40.77Improved
Use pixel-wise voting with RANSAC-based keypoint localizationPVNet · LINEMODADD(-S): 55.95 -> 86.27Improved
Use PVNet for keypoint localization rather than the strongest compared methodPose estimation · Occlusion LINEMODADD(-S): 30.4 -> 40.77Improved
Use PVNet for pose estimationPose estimation · YCB-VideoADD(-S) AUC: 72.8 -> 73.4Improved
Train and test the vector-field voting approach on cropped images with only 40% to 60% of the target visiblePVNet · Truncation LINEMODADD(-S)Mixed

Later papers that compared with this method

17 later accepted papers report PVNet as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.

9 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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