AI Paper Atlas

Research map / 3D vision / Human pose estimation

GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild

Alexander Grabner, Peter M. Roth, Vincent Lepetit

ICCV 2019 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 20 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
add joint 3D pose and focal length refinement to the initial EPnP solution (Ours-LF) (ablation)Ours-LF · Pix3D meanAcc_P0.1: 84.7% -> 85.5%Improved
add joint 3D pose and focal length refinement to the initial EPnP solution (Ours-BB) (ablation)Ours-BB · Pix3D meanAcc_P0.1: 86.8% -> 88.0%Improved
add joint refinement (MedErr_P) (ablation)Ours-BB · Pix3D meanMedErr_P x10^2: 3.87 -> 3.66Improved
use Cauchy loss PnP instead of standard squared loss (ablation)Ours-LF · Pix3D meanAcc_P0.1: 85.3% -> 85.5%No clear effect
use Cauchy loss PnP instead of standard squared loss (ablation)Ours-BB · Pix3D meanAcc_P0.1: 87.5% -> 88.0%No clear effect
use RANSAC PnP instead of standard PnP (ablation)Ours-BB · Pix3D meanMedErr_P x10^2: 3.68 -> 3.68No clear effect
explicitly estimate and integrate focal length in pose estimationOurs-LF vs prior SOTA · Pix3D meanMedErr_t x10^1: 2.52 -> 1.85Improved
explicitly estimate and integrate focal length in pose estimationOurs-BB vs prior SOTA · Pix3D meanAcc_P0.1: 71.5% -> 88.0%Improved
explicitly estimate and integrate focal length in pose estimationOurs-BB vs prior SOTA · Comp carMedErr_t x10^1: 3.30 -> 2.55Improved
explicitly estimate and integrate focal length in pose estimationOurs-BB vs prior SOTA · Stanford carAcc_P0.1: 76.4% -> 96.5%Improved
initialize geometric optimization with predicted focal length instead of constant median focal length (ablation)GP2C · Pix3DAcc_R,tImproved
initialize with ground truth focal length instead of predicted (ablation)GP2C · Pix3DAcc_R,tImproved

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