AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Generative Layout Modeling Using Constraint Graphs

Wamiq Para, Paul Guerrero, Tom Kelly, Leonidas J. Guibas, Peter Wonka

ICCV 2021 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 97 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 free generation (no boundary input) instead of boundary-conditioned generationconstraint-graph layout model · RPLAN floor plansFID: 27.27 -> 21.47Improved
condition on ground-truth exterior boundaryconstraint-graph layout model · RPLAN floor planss_avg: 1.00 -> 1.03No clear effect
condition on ground-truth exterior boundaryconstraint-graph layout model · LIFULL floor planss_avg: 1.00 -> 2.30Hurt
condition on ground-truth exterior boundaryconstraint-graph layout model · LIFULL floor plansFID: 26.15 -> 31.94Hurt
use proposed three-step constraint graph model instead of StyleGAN image generationfloor plan generation · RPLAN floor planss_avg: 19.67 -> 1.00Improved
use proposed model instead of StyleGANfloor plan generation · LIFULL floor planss_avg: 16.27 -> 1.00Improved
use proposed free generation instead of RPLAN baseline (which gets ground-truth boundary)floor plan generation · RPLAN floor plansFID: 21.29 -> 21.47No clear effect
use proposed free generation instead of RPLAN baselinefloor plan generation · LIFULL floor planss_avg: 15.55 -> 1.00Improved
use proposed model instead of Graph2Plan (which gets ground-truth layout graph)floor plan generation · RPLAN floor planss_avg: 8.46 -> 1.00Improved
use proposed model instead of StyleGAN for furniture layoutsfurniture layout generation · Furniture layoutss_avg: 9.94 -> 1.00Improved

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