AI Paper Atlas

Research map / Optimization / Distributed and compressed

Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus

Runze Zhang, Siyu Zhu, Tian Fang, Long Quan

ICCV 2017 · Optimization › Distributed and compressed · approach: Decentralized optimization algorithms · 79 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
add over-relaxation (ablation)camera consensus · Buildingsreprojection error (px): 1.35 -> 1.23Improved
add over-relaxation (ablation)camera consensus · Townreprojection error (px): 1.87 -> 1.76Improved
add over-relaxation (ablation)camera consensus · Final 961iterations to converge: 30 -> 22Improved
add self-adaption of penalty (ablation)camera consensus · Buildingsiterations to converge: 100 -> 64Improved
add self-adaption of penalty (ablation)camera consensus · Roman Forumreprojection error (px): 0.590 -> 0.536Improved
add self-adaption of penalty (ablation)camera consensus · Veniceiterations to converge: 12 -> 16Hurt
add self-adaption of penalty (ablation)camera consensus · Streetreprojection error (px): 1.05 -> 1.04No clear effect
camera consensus instead of point consensusdistributed BA · Towndata broadcast per iteration (MB): 342 -> 17.3Improved
camera consensus instead of point consensusdistributed BA · Final 13682data broadcast per iteration (MB): 106 -> 25.8Improved
camera consensus instead of point consensusdistributed BA · Cityreprojection error (px): 1.41 -> 1.36Improved
camera consensus instead of point consensusdistributed BA · Veniceiterations to converge: 20 -> 16Improved
normalized-cut splitting instead of KD-tree splitting (ablation)camera consensus · Final 13682cameras broadcast per iteration: 511k -> 282kImproved

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