AI Paper Atlas

Research map / 3D vision / Human pose estimation

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Martin Cífka, Georgy Ponimatkin, Yann Labbé, Bryan Christopher Russell, Mathieu Aubry, Vladimír Petrík, Josef Šivic

TPAMI 2024 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 6 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
sample synthetic pose and focal length from a parametric distribution instead of uniform (ablation)FocalPose++ · Pix3D sofaMedErr_R: 2.95 -> 2.77Improved
sample from a nonparametric distribution instead of uniform (ablation)FocalPose++ · Pix3D sofaMedErr_R: 2.95 -> 2.82Improved
add 0.5% real images to synthetic training (ablation)FocalPose coarse model · Pix3D sofaMedErr_R: 5.44 -> 2.98Improved
add synthetic data to real-only training (ablation)FocalPose coarse model · Pix3D sofaMedErr_R: 4.13 -> 2.98Improved
raise real fraction from 0.5% to 5% (ablation)FocalPose coarse model · Pix3D sofaMedErr_R: 2.98 -> 3.08No clear effect
replace DINO with ML-Decoder+1k retrieval (ablation)FocalPose++ · Pix3D model retrievalaccuracy: 62.1% -> 77.6%Improved
replace DINO with ML-Decoder+1k retrieval (ablation)FocalPose++ · Pix3D sofaMedErr_R: 3.00 -> 2.77Improved
add 1000 synthetic images to classifier training (ablation)ML-Decoder · Pix3D model retrievalaccuracy: 72.8% -> 77.6%Improved
add 1000 synthetic images to classifier training (ablation)ML-Decoder · Stanford Cars model retrievalaccuracy: 95.1% -> 94.7%Hurt
use refined x/y update rule (ablation)FocalPose++ · Pix3D sofaMedErr_R: 2.81 -> 2.77Improved
add 2D reprojection loss to Huber loss (ablation)FocalPose refiner · Pix3D sofa (FocalPose loss ablation)MedErr_R: 6.61 -> 3.28Improved
disentangle focal length and pose in reprojection loss (ablation)FocalPose refiner · Pix3D sofa (FocalPose loss ablation)MedErr_R: 3.28 -> 2.98Improved

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