AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

On the Recovery of Cameras from Fundamental Matrices

Rakshith Madhavan, Federica Arrigoni

ICCV 2025 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 1 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 GPSFM with ANGLE-IT-IRLS for camera recoveryGPSFM · 25 real projective SfM sequencesreprojection error: better in 20 out of 25 sequencesImproved
replace GPSFM-SYNCH with ANGLE-IT-IRLS for camera recoveryGPSFM-SYNCH · 25 real projective SfM sequencesreprojection error: better in 21 out of 25 casesImproved
replace GPSFM-SYNCH with ANGLE-IT-IRLSGPSFM-SYNCH · Toronto Universityreprojection error (px): 18.28 -> 64.10Hurt
replace GPSFM-SYNCH with ANGLE-IT-IRLSGPSFM-SYNCH · Alcatraz Water Towerreprojection error (px): 19.76 -> 36.54Hurt
replace GPSFM with ANGLE-IT-IRLSGPSFM · Nijoreprojection error (px): 29.85 -> 17.38Improved
replace GPSFM-SYNCH with ANGLE-IT-IRLSGPSFM-SYNCH · De Guerrereprojection error (px): 1.33 -> 1.82Hurt
use ANGLE-IT-IRLS on pruned graph with a camera not in any tripletGPSFM · Sphinx (pruned graph)reprojection error (px): 8.16 -> 4.71Improved
use ANGLE-IT-IRLS on pruned graph with a camera not in any tripletGPSFM-SYNCH · Sphinx (pruned graph)reprojection error (px): 7.10 -> 4.71Improved
add IRLS robust reweighting (ablation)LS-SVD · synthetic, increasing outlier densitycamera error (degrees)Improved
add IRLS robust reweighting (ablation)ANGLE-IT · synthetic, increasing outlier densitycamera error (degrees)Improved
use unsquared angular distance (ANGLE-IT) instead of least squares (LS-SVD) (ablation)alternating optimization · synthetic, outliers up to 40% without IRLScamera error (degrees)Improved
use angular distance (ANGLE-IT) instead of least squares (LS-SVD) (ablation)alternating optimization · synthetic, increasing noise (n=25, rho=0.4)camera error (degrees)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