AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising

Mohammad Amin Shabani, Sepidehsadat Hosseini, Yasutaka Furukawa

CVPR 2023 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 103 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 joint continuous noise prediction and discrete coordinate denoising (ablation)HouseDiffusion · RPLANDiversity (FID): 38.8\scalebox{0.8}{$\pm$0.9} -> 9.5\scalebox{0.8}{$\pm$0.1}Improved
Use joint continuous noise prediction and discrete coordinate denoising (ablation)HouseDiffusion · RPLANCompatibility: 2.2\scalebox{0.8}{$\pm$0.0} -> 2.5\scalebox{0.8}{$\pm$0.0}Hurt
Replace continuous-plus-discrete denoising with discrete-only AnalogBits (ablation)HouseDiffusion · RPLANCompatibility: 2.5\scalebox{0.8}{$\pm$0.0} -> 6.0\scalebox{0.8}{$\pm$0.03}Hurt
Add Component-wise Self Attention (ablation)HouseDiffusion · RPLANCompatibility: 2.9\scalebox{0.8}{$\pm$0.0} -> 2.5\scalebox{0.8}{$\pm$0.0}Improved
Add Global Self Attention (ablation)HouseDiffusion · RPLANDiversity (FID): 12.8\scalebox{0.8}{$\pm$0.2} -> 9.5\scalebox{0.8}{$\pm$0.1}Improved
Add Relational Cross Attention (ablation)HouseDiffusion · RPLANCompatibility: 6.8\scalebox{0.8}{$\pm$0.0} -> 2.5\scalebox{0.8}{$\pm$0.0}Improved
Replace the three attention types with more GSA layers (ablation)HouseDiffusion · RPLANCompatibility: 6.5\scalebox{0.8}{$\pm$0.0} -> 2.5\scalebox{0.8}{$\pm$0.0}Hurt
Augment corners with sampled points along their walls (ablation)HouseDiffusion · RPLANCompatibility: 3\scalebox{0.8}{$\pm$0.0} -> 2.5\scalebox{0.8}{$\pm$0.0}Improved
Augment corners with sampled points along their walls (ablation)HouseDiffusion · RPLANDiversity (FID): 10.0\scalebox{0.8}{$\pm$0.3} -> 9.5\scalebox{0.8}{$\pm$0.1}Improved
Use discrete denoising for too few or too many final steps (ablation)HouseDiffusion · RPLANPerformanceHurt
Generate vector floorplans with HouseDiffusion instead of House-GAN++RPLAN · RPLANDiversity (FID): 30.4\scalebox{0.8}{$\pm$4.4} -> 9.5\scalebox{0.8}{$\pm$0.1}Improved
Generate vector floorplans with HouseDiffusion instead of House-GAN++RPLAN · RPLANRealism: -0.52 -> -0.19Improved

Later papers that compared with this method

2 later accepted papers report HouseDiffusion as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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