AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deterministic Object Pose Confidence Region Estimation

Jinghao Wang, Zhang Li, Zi Wang, Banglei Guan, Yang Shang, Qifeng Yu

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 2 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
regress Gaussian keypoint distributions and propagate through IFT instead of heatmap keypoints plus random samplingpose confidence region estimation · LMOtranslation region volume: 109.9 -> 8.6Improved
replace sampling with IFT deterministic propagationpose confidence region estimation · SPEEDrotation region volume: 210.6 -> 0.2Improved
replace sampling-based with deterministic propagationpose confidence region estimation · LMOtranslation coverage rate: 96.61 -> 83.24Hurt
replace sampling-based with deterministic propagationpose confidence region estimation · SPEEDtranslation coverage rate: 6.40 -> 86.69Improved
use regression-based keypoint detection instead of heatmap-basedkeypoint detection · SPEEDkeypoint reprojection accuracy: 57.80 -> 97.09Improved
use regression-based keypoint detection instead of heatmap-basedkeypoint detection · LMOkeypoint reprojection accuracy: 67.33 -> 74.45Improved
use regression-based keypoint detection instead of heatmapskeypoint region time · LMOtime (s): 0.0076 -> 0.0038Improved
use Yang et al. heatmap keypoints with deterministic propagation versus our regression keypoints (ablation)LMO · LMO, epsilon=0.1rotation region volume: 100.1 -> 91.3No clear effect
use heatmap keypoints on occlusion-free SPEED (ablation)Yang et al. heatmap + deterministic propagation · SPEEDtranslation region volume: 0.7 -> 73.4Hurt
apply ICP calibration to our regressed Gaussianskeypoint confidence region · LMO and SPEED, epsilon=0.12D keypoint coverage rate: 90.65 vs 91.16 (LMO); 89.66 vs 88.88 (SPEED)No clear effect

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