AI Paper Atlas

Research map / 3D vision / Human pose estimation

Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features

Marcus Valtonen Örnhag, Alberto Jaenal Gálvez, Stefan Adalbjörnsson

ECCV 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 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 proposed UP1PfAC instead of P4Pf for unknown-focal localizationGC-RANSAC pipeline · Cambridge GreatCourt (SuperPoint+LightGlue)median position error (cm): 61.5 -> 57.7Improved
use proposed UP1PfAC instead of P4Pf for unknown-focal localizationGC-RANSAC pipeline · Cambridge OldHospital (SIFT+NN)median position error (cm): 51.1 -> 48.4Improved
use semi-calibrated UP1PfAC instead of calibrated UP2P (known f)GC-RANSAC pipeline · Cambridge GreatCourt (SuperPoint+LightGlue)median position error (cm): 31.6 -> 57.7Hurt
use UP1PfAC instead of P4Pf for rotationGC-RANSAC pipeline · Cambridge OldHospital (SuperPoint+LightGlue)median rotation error (deg): 0.42 -> 0.38Improved
use UP1PfAC instead of P4Pf on Aachen night imagesGC-RANSAC pipeline · Aachen Night (SuperPoint+LightGlue, 0.25m/2deg)recall (%): 54.5 -> 60.2Improved
use UP2PfORI instead of P4Pf on Aachen night imagesGC-RANSAC pipeline · Aachen Night (SuperPoint+LightGlue, 0.25m/2deg)recall (%): 54.5 -> 62.3Improved
use UP1PfAC instead of P4Pf on Aachen day imagesGC-RANSAC pipeline · Aachen Day (SuperPoint+LightGlue, 0.25m/2deg)recall (%): 46.1 -> 48.5Improved
use semi-calibrated UP1PfAC instead of calibrated UP2PGC-RANSAC pipeline · Aachen Day (SuperPoint+LightGlue, 0.25m/2deg)recall (%): 71.8 -> 48.5Hurt
use UP1PfAC instead of P4Pf for focal length estimationGC-RANSAC pipeline · Aachen (SIFT+NN)focal length error: 0.019 -> 0.017Improved
use 2-point UP2PfORI instead of 1-point UP1PfACproposed solvers · Cambridge and Aachenaccuracy: 2149 ns vs 2586 nsMixed
use UP1PfAC instead of calibrated UP2P in runtimesolver · Solver runtimemedian time (ns): 484 -> 2586Hurt
use UP1PfAC instead of P3.5Pf in runtimesolver · Solver runtimemedian time (ns): 19118 -> 2586Improved

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