AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation

Liu He, Daniel Aliaga

ECCV 2024 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 14 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 GAT backbone in block VAE instead of GCN or SAGE (ablation)BVAE · Block-level reconstructionOverlap (%): 0.45 -> 0.17Improved
use per-dimension quantization (L=20) instead of trainable VQ (ablation)BVAE latent quantization · Block quantizationGeom-E (%): 5.78 -> 0.89Improved
use per-dimension quantization instead of KMeans clustering (ablation)BVAE latent quantization · Block quantizationGeom-E (%): 17.85 -> 0.89Improved
increase quantization levels per dimension from 20 to 30 (ablation)DIM-Q · Block quantizationGeom-E (%): 0.89 -> 0.78No clear effect
use GAT message passing instead of GCN in city-level GMAE (ablation)GMAE · City-scale layoutFID: 52.95 -> 23.63Improved
increase encoder depth from 1 to 3 hops (ablation)GMAE · City-scale layoutFID: 43.75 -> 23.63Improved
increase encoder depth from 3 to 4 (ablation)GMAE · City-scale layoutFID: 23.63 -> 24.59No clear effect
use GAT decoder with remasking instead of MLP decoder (ablation)GMAE · City-scale layoutFID: 23.63 -> 48.24Hurt
use dynamic large mask ratio instead of fixed 0.15 (ablation)GMAE training · City-scale layoutFID: 49.50 -> 23.63Improved
use cosine scheduling instead of linear or logarithmic (ablation)GMAE iterative generation · City-scale layoutFID: 37.42 -> 23.63 (linear), 63.25 (log)Improved
use more iterations T=12 instead of single pass (ablation)GMAE iterative generation · City-scale layoutFID: 76.12 -> 23.63Improved
COHO vs baselines on overlap metricCOHO · US city-scale layout testOverlap: VTN 1.24 vs COHO 1.27Mixed

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