AI Paper Atlas

Research map / 3D vision / Human pose estimation

Expert Sample Consensus Applied to Camera Re-Localization

Eric Brachmann, Carsten Rother

ICCV 2019 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 129 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 ESAC instead of Expert Selectionexpert ensemble · Toy problemparameter accuracy: +3.9%Improved
use ESAC instead of Expert Selectionexpert ensemble · Toy problemmodel type classification accuracy: 11.5%Improved
limit ESAC to top 2 experts per test image vs Expert Selection (ablation)ESAC · 19Scenespose accuracy: +19.7%Improved
use ESAC with distributed hypotheses instead of a single monolithic DSAC++DSAC++ · 19Scenespose accuracy 5cm/5deg: 53.3% -> 88.1%Improved
end-to-end training of gating network, experts or all (ablation)ESAC · 19Scenespose accuracyImproved
end-to-end training evaluated at stricter 2cm/2deg threshold (ablation)ESAC · 19Scenespose accuracy: >10%Improved
replace VGG with ResNet expertsDSAC++ architecture · 7Scenes/12Scenespose accuracy and memory: 210MB -> 28MBNo clear effect
increase number of experts (ablation)ESAC · Dubrovnik/Aachen Daypose accuracyNo 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