AI Paper Atlas

Research map / Image generation / GANs

House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa

ECCV 2020 · Image generation › GANs · approach: Stabilized GAN training

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 room connectivity to room count and type (ablation)House-GAN · House layout, 13+ roomscompatibility graph edit distance: 21.4 -> 10.8Improved
add room connectivity to room count and type (ablation)House-GAN · House layout, 4-6 roomscompatibility graph edit distance: 2.2 -> 1.1Improved
add room type to room count (ablation)House-GAN · House layout, 13+ roomscompatibility graph edit distance: 37.3 -> 21.4Improved
add room count (relational graph) to no graph information (ablation)House-GAN · House layout, 13+ roomscompatibility graph edit distance: 32.2 -> 37.3Hurt
add room count (relational graph) to no graph information (ablation)House-GAN · House layout, 1-3 roomscompatibility graph edit distance: 28.5 -> 0.6Improved
replace GCN vector message passing with Conv-MPN feature volumesHouse-GAN · House layout, 13+ roomsdiversity FID: 31.5 -> 20.1Improved
replace GCN with Conv-MPNHouse-GAN · House layout, 13+ roomscompatibility graph edit distance: 3.7 -> 10.8Hurt
replace CNN-only generator with relational House-GANHouse-GAN · House layout, 13+ roomsdiversity FID: 90.0 -> 20.1Improved
replace GCN with Conv-MPNHouse-GAN · House layout, all groupsrealism user score: 0.11 -> 0.15Improved
add spectral normalization or per-room discriminator (ablation)House-GAN · House layoutqualityNo clear effect

Later papers that compared with this method

5 later accepted papers report HouseGAN++ as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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