AI Paper Atlas

Research map / 3D vision / Depth and stereo

View-graph Selection Framework for SfM

Rajvi Shah, Visesh Chari, P J Narayanan

ECCV 2018 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 12 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
select edges with view-graph selection instead of full graphGlobal SfM · Internet landmarks - PantheonSfM runtime: 3601 -> 1785Improved
select edges with view-graph selection instead of full graphGlobal SfM · Internet landmarks - Notre DameSfM runtime: 1760 -> 1151Improved
select edges with view-graph selection instead of full graphGlobal SfM · Internet landmarks - Pantheonrotation error: 0.125 -> 0.098Improved
select edges with view-graph selection instead of full graphGlobal SfM · Internet landmarks - St. Petersrotation error: 0.028 -> 0.037Hurt
select edges with view-graph selection instead of full graphGlobal SfM · Internet landmarks - Castle (MVS)translation error: 7.49 -> 1.29Improved
select edges with view-graph selection instead of full graphIncremental SfM · MVS benchmarkreconstruction accuracyNo clear effect
use random costs for selection (ablation)View-graph selection · Ambiguous datasetssuccessful reconstruction: fails on all datasetsHurt
use baseline priors based costs (ablation)View-graph selection · Ambiguous datasetssuccessful reconstruction: fails on all but booksHurt
add disambiguation priors to general reconstruction priors (ablation)View-graph selection · Ambiguous datasetssuccessful reconstruction: fails on cup and cereal onlyImproved
use context similarity prior alone (ablation)View-graph selection · Ambiguous small datasets (6 lab-style)successful reconstruction: 6 of 6 correctImproved
combine context and loop priors (ablation)View-graph selection · Ambiguous datasetsrange of flow valuesImproved
add multiple-motions prior to context and loop priors (ablation)View-graph selection · Large ambiguous datasetssuccessful reconstructionNo 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