AI Paper Atlas

Research map / 3D vision / Human pose estimation

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

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

TPAMI 2020 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 157 citations (OpenAlex)

Read the paperCheck 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 pixel-wise voting keypoint localization instead of coordinate regression (Tekin) (ablation)PVNet · Occlusion LINEMODADD(-S) accuracy: 6.42 -> 33.88Improved
use FPS surface keypoints instead of bounding-box corners (ablation)PVNet · Occlusion LINEMODADD(-S) accuracy: 33.88 -> 39.76Improved
increase FPS keypoints from 4 to 8 (ablation)PVNet · Occlusion LINEMODADD(-S) accuracy: 17.96 -> 39.76Improved
increase FPS keypoints from 8 to 12 (ablation)PVNet · Occlusion LINEMODADD(-S) accuracy: 39.76 -> 39.92No clear effect
add uncertainty-driven PnP instead of EPnP (ablation)PVNet FPS 8 · Occlusion LINEMODADD(-S) accuracy: 39.76 -> 40.77Improved
PVNet versus BB8 without refinementPVNet · LINEMOD2D projection accuracy: 83.9 -> 99.00Improved
PVNet versus Tekin on ADD(-S)PVNet · LINEMODADD(-S) accuracy: 55.95 -> 86.27Improved
PVNet versus SSD-6D with refinementPVNet · LINEMODADD(-S) accuracy: 79 -> 86.27Improved
PVNet versus Oberweger on 2D projectionPVNet · Occlusion LINEMOD2D projection accuracy: 60.9 -> 61.06No clear effect
PVNet versus Oberweger on ADD(-S)PVNet · Occlusion LINEMODADD(-S) accuracy: 30.4 -> 40.77Improved
PVNet versus Oberweger on ADD(-S) AUCPVNet · YCB-VideoADD(-S) AUC: 72.8 -> 73.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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