AI Paper Atlas

Research map / 3D vision / Face and shape

Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization

Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof

ECCV 2018 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 32 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 Labatut visibility energy with the proposed normalized visibility energyvisibility-only reconstruction · Residential Areamean error (m): 0.035 -> 0.034Improved
replace Labatut visibility energy with the proposed normalized visibility energyvisibility-only reconstruction · Fountain-P11mean error (m): 0.037 -> 0.034Improved
replace Labatut visibility energy with the proposed normalized visibility energyvisibility-only reconstruction · Fountain-P11std of error (m): 0.146 -> 0.135Improved
replace Labatut visibility energy with the proposed normalized visibility energyvisibility-only reconstruction · Residential Areastd of error (m): 0.071 -> 0.069Improved
add semantic class-specific processing (Poisson surroundings, building-only planes) (ablation)Proposed pipeline · House and Residential Areavisual quality of surroundingsImproved
use line-based plane detection instead of point-based RANSACplane detection · urban facadesplane completenessImproved
Proposed vs Poissonreconstruction · Housemean error (m): 0.165 -> 0.126Improved
Proposed vs Poissonreconstruction · Residential Areamean error (m): 0.101 -> 0.055Improved
Proposed vs Holzmann et al.reconstruction · Residential Areamean error (m): 0.415 -> 0.055Improved
apply lossless Quadric Edge Collapse to proposed mesh rather than Poisson meshmesh simplification · Houseface reduction factor r: 0.154 vs 0.929Improved

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