AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Privacy Preserving Structure-from-Motion

Marcel Geppert, Viktor Larsson, Pablo Speciale, Johannes L. Schönberger, Marc Pollefeys

ECCV 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification

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 privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Madrid Metropolisregistered images: 279 -> 377Improved
use privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Gendarmenmarktregistered images: 825 -> 810No clear effect
use privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Madrid Metropolismedian point reprojection error: 0.45 -> 1.13Hurt
use privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Tower of Londonmedian point reprojection error: 0.38 -> 0.54Hurt
use privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Alamomean track length: 12.8 -> 21.9Improved
use privacy-preserving random line features instead of point featuresCOLMAP · Internet photos: Tower of Londonnumber of 3D points: 146k -> 93kHurt
use privacy-preserving lines instead of pointsCOLMAP · Strecha castle-P30position error (cm): 3cm -> 4.00Hurt
use privacy-preserving lines instead of pointsCOLMAP · Speciale et al. six datasetsrecall at 25cm threshold: 90Mixed
select 50% of features as gravity-aligned instead of a smaller share (ablation)privacy preserving SfM initialization · Strecha and Speciale datasetsinitialization tracksImproved

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