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

Shabani, Mohammad Amin; Hosseini, Sepidehsadat; Furukawa, Yasutaka

doi:10.1109/cvpr52729.2023.00529

Cited by 21 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unconstrained generation. We have observed that some existing layout generative models [NCC*20,NHC*21,SHF23] only use bubble diagrams as inputs. Therefore, we have also tested the ability of BubbleFormer to generate bubble diagrams without any input, allowing our method to drive this type of layout generation approach.…”

Section: Methodsmentioning

confidence: 99%

BubbleFormer: Bubble Diagram Generation via Dual Transformer Models

Sun,

Zheng,

Zhang

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Bubble diagrams serve as a crucial tool in the field of architectural planning and graphic design. With the surge of Artificial Intelligence Generated Content (AIGC), there has been a continuous emergence of research and development efforts focused on utilizing bubble diagrams for layout design and generation. However, there is a lack of research efforts focused on bubble diagram generation. In this paper, we propose a novel generative model, BubbleFormer, for generating diverse and plausible bubble diagrams. BubbleFormer consists of two improved Transformer networks: NodeFormer and EdgeFormer. These networks generate nodes and edges of the bubble diagram, respectively. To enhance the generation diversity, a VAE module is incorporated into BubbleFormer, allowing for the sampling and generation of numerous high‐quality bubble diagrams. BubbleFormer is trained end‐to‐end and evaluated through qualitative and quantitative experiments. The results demonstrate that BubbleFormer can generate convincing and diverse bubble diagrams, which in turn drive downstream tasks to produce high‐quality layout plans. The model also shows generalization capabilities in other layout generation tasks and outperforms state‐of‐the‐art techniques in terms of quality and diversity. In previous work, bubble diagrams as input are provided by users, and as a result, our bubble diagram generative model fills a significant gap in automated layout generation driven by bubble diagrams, thereby enabling an end‐to‐end layout design and generation. Code for this paper is at https://github.com/cgjiahui/BubbleFormer.

show abstract

Section: Methodsmentioning

confidence: 99%

BubbleFormer: Bubble Diagram Generation via Dual Transformer Models

Sun,

Zheng,

Zhang

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Diffusion-based methods arouse wide attention due to their excellent performance in generative tasks across multiple fields, such as computer vision (Avrahami, Lischinski, and Fried 2022;Ho et al 2022;Cai et al 2020;Luo and Hu 2021), natural language processing (Hoogeboom et al 2021;Savinov et al 2022), as well as various interdisciplinary tasks (Shabani, Hosseini, and Furukawa 2023;Lei et al 2023) et al…”

Section: Related Work Diffusion Modelsmentioning

confidence: 99%

Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation

Xu,

Wang,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms in molecules allow connections to multiple atoms through single bonds, solely using pair-wise distance to model molecule geometries is insufficient. Therefore, the first one involves proposing an effective neural network as the denoising kernel that is capable to capture complex multi-body interatomic relationships and learn high-quality features. Due to the discrete nature of graphs, mainstream diffusion-based methods for molecules heavily rely on predefined rules and generate edges in an indirect manner. The second challenge involves accommodating molecule generation to diffusion and accurately predicting the existence of bonds. In our research, we view the iterative way of updating molecule conformations in diffusion process is consistent with molecular dynamics and introduce a novel molecule generation method named Geometric-Facilitated Molecular Diffusion (GFMDiff). For the first challenge, we introduce a Dual-track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations which contribute to accurate predictions of features and geometries. As for the second challenge, we design Geometric-facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space. Comprehensive experiments on current benchmarks demonstrate the superiority of GFMDiff.

show abstract

“…Current approaches for within-unit room divisions are an active area of computer graphics research but are not currently used in the architecture industry due to a wide range of limitations: Being only able to represent rectangular [14] or orthogonal boundary conditions [15], or responding to only either topological or spatial or boundary constraints [16], [17], [18], [19], [20]. On a technical level, ML-based models create neural networks that relate the geometric graph structures from room walls to an adjacency graph (vector [21], [22] or pixel based [23]) or use reinforcement learning to subdivide a space [24]. This results in a linear, one-sided generation process, where a room adjacency graph is converted into a visually real and geometrically valid floor plan.…”

Section: Introductionmentioning

confidence: 99%

A hypergraph model shows the carbon reduction potential of effective space use in housing

Weber,

Mueller,

Reinhart

2024

Preprint

View full text Add to dashboard Cite

Humans spend over 90% of their time in buildings which account for 40% of anthropogenic greenhouse gas (GHG) emissions, making buildings the leading cause of climate change. To incentivize more sustainable construction, building codes are used to enforce indoor comfort standards and maximum energy use. However, they currently only reward energy efficiency measures such as equipment or envelope upgrades and disregard the actual spatial configuration and usage. Using a new hypergraph model that encodes building floorplan organization and facilitates automatic geometry creation, we demonstrate that space efficiency outperforms envelope upgrades in terms of operational carbon emissions in 72%, 61% and 33% of surveyed buildings in Zurich, New York, and Singapore. Automatically generated floorplans for a case study in Zurich further increase access to daylight by up to 24%, revealing that auto-generated floorplans have the potential to improve the quality of residential spaces in terms of environmental performance and access to daylight.

show abstract

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

Cited by 21 publications

References 27 publications

BubbleFormer: Bubble Diagram Generation via Dual Transformer Models

BubbleFormer: Bubble Diagram Generation via Dual Transformer Models

Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation

A hypergraph model shows the carbon reduction potential of effective space use in housing

Contact Info

Product

Resources

About