AI Paper Atlas

Research map / 3D vision / Human pose estimation

P1AC: Revisiting Absolute Pose From a Single Affine Correspondence

Jonathan Ventura, Zuzana Kukelova, Torsten Sattler, Dániel Baráth

ICCV 2023 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 13 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
replace P3P with P1AC as minimal solver in GC-RANSACGC-RANSAC localization · Cambridge Landmarks avgrecall 0.1m/1deg (%): 54.62 -> 65.08Improved
replace P3P with P1AC as minimal solver in GC-RANSACGC-RANSAC localization · Aachen Day-Night Nightrecall 5m/10deg (%): 74.3 -> 82.2Improved
replace P3P with P1AC on Aachen Day sequenceGC-RANSAC localization · Aachen Day-Night Dayrecall 0.25m/2deg (%): 62.0 -> 62.0No clear effect
use P1AC instead of DPR and IPPE (no virtual warping)single-AC solvers · Cambridge Landmarks avgrecall 0.1m/1deg (%): 63.48 (DPR) -> 65.08Improved
increase perspective skew of affine correspondence (ablation)DPR solver · synthetic 1M instancesrotation accuracyHurt
use vanilla RANSAC with P1AC instead of P3P at realistic noisesynthetic robust estimation · synthetic outlier ratios 0-0.9average rotation error (deg): 0.056 -> 0.450Hurt
add local optimization (LO-RANSAC) with P1AC (ablation)P1AC · synthetic robust estimationaverage rotation error (deg): 0.450 -> 0.085Improved
drop SNN ratio filtering for P1AC on Cambridge (ablation)P1AC · Cambridge Landmarksaccuracy and inlier countImproved
add affine and normal noise to P1AC input (ablation)P1AC solver · synthetic noisepose errorHurt
P1AC runtime in GC-RANSAC vs P3PGC-RANSAC · Cambridge Landmarkstime (s): Great Court 0.14 -> 0.26Hurt

Later papers that compared with this method

1 later accepted paper reports P1AC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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