AI Paper Atlas

Research map / 3D vision / Face and shape

Raster-To-Vector: Revisiting Floorplan Transformation

Chen Liu, Jiajun Wu, Pushmeet Kohli, Yasutaka Furukawa

ICCV 2017 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 270 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 integer programming (full IP) after the CNN junction detection (ablation)Raster-to-vector pipeline · Floorplan benchmark - wall junctionprecision (%): 70.7 -> 94.7Improved
add integer programming (ablation)Raster-to-vector pipeline · Floorplan benchmark - openingprecision (%): 67.9 -> 91.9Improved
add integer programming (ablation)Raster-to-vector pipeline · Floorplan benchmark - iconprecision (%): 22.3 -> 84.0Improved
add integer programming (ablation)Raster-to-vector pipeline · Floorplan benchmark - roomprecision (%): 80.9 -> 84.5Improved
add integer programming (ablation)Raster-to-vector pipeline · Floorplan benchmark - wall junctionrecall (%): 95.1 -> 91.7Hurt
add integer programming (ablation)Raster-to-vector pipeline · Floorplan benchmark - roomrecall (%): 78.5 -> 88.4Improved
add mutual exclusion constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - openingprecision (%): 68.5 -> 91.9Improved
add mutual exclusion constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - iconprecision (%): 22.0 -> 84.0Improved
add mutual exclusion constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - wall junctionprecision (%): 92.8 -> 94.7Improved
add mutual exclusion constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - roomrecall (%): 87.5 -> 88.4Mixed
add loop constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - roomprecision (%): 82.5 -> 84.5Improved
add loop constraints to IP (ablation)Raster-to-vector pipeline · Floorplan benchmark - iconrecall (%): 75.0 -> 74.6No 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