AI Paper Atlas

Research map / Image generation / GANs

Roof-GAN: Learning To Generate Roof Geometry and Relations for Residential Houses

Yiming Qian, Hao Zhang, Yasutaka Furukawa

CVPR 2021 · Image generation › GANs · approach: Large-scale GAN latent analysis · 25 citations (OpenAlex)

Check 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 generated pairwise relationships, a relationship discriminator, and differentiable relationship-aware geometry processing (ablation)Roof-GAN · Residential roof generation test setRMMD: 6.61 -> 6.20Improved
Add differentiable vectorization and relationship enforcement during training (ablation)Roof-GAN · Residential roof generation test setRMMD: 6.48 -> 6.20Improved
Encode pairwise relationships in the serialized representationPQ-Net · Residential roof generation test setRMMD: 7.80 -> 6.97Improved
Encode pairwise relationships in the serialized representationPQ-Net · Residential roof generation test setFID: 12.0 -> 13.5Hurt
Use Roof-GAN's raster geometry representation instead of House-GAN's vectorized facet-angle and primitive-type representationHouse-GAN · Residential roof generation test setFID: 18.4 -> 10.6Improved
Use Roof-GAN's raster geometry representation instead of House-GAN's vectorized facet-angle and primitive-type representationHouse-GAN · Residential roof generation test setRMMD: 7.43 -> 6.61Improved
Generate with Roof-GAN rather than PQ-NetRoof-GAN · Cross-validation, 3 primitivesRMMD: 10.4 -> 7.5Improved
Generate with Roof-GAN rather than House-GANRoof-GAN · Cross-validation, 3 primitivesRMMD: 8.5 -> 7.5Improved
Generate with Roof-GAN rather than PQ-NetRoof-GAN · Cross-validation, 4 primitivesFID: 14.6 -> 13.8Improved
Generate with Roof-GAN rather than PQ-NetRoof-GAN · Cross-validation, 4 primitivesRMMD: 12.9 -> 10.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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