HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation
Floorplan synthesis is the process of generating new, realistic floor plans for buildings and homes using machine learning and generative models. In recent years, various generative methods, including GANs and diffusion models, have been utilized for the task of floorplan generation, demonstrating p...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10658971/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849697436267708416 |
|---|---|
| author | Azmeraw Bekele Yenew Beakal Gizachew Assefa Elefelious Getachew Belay |
| author_facet | Azmeraw Bekele Yenew Beakal Gizachew Assefa Elefelious Getachew Belay |
| author_sort | Azmeraw Bekele Yenew |
| collection | DOAJ |
| description | Floorplan synthesis is the process of generating new, realistic floor plans for buildings and homes using machine learning and generative models. In recent years, various generative methods, including GANs and diffusion models, have been utilized for the task of floorplan generation, demonstrating promising advancements in architectural design and planning. However, despite their potential, these methods face unique challenges like mode collapse, training instability, and sampling time, which require innovative solutions to overcome for further progress in this field. To address these issues, various techniques such as regualrization techniques, architectural modifications, and optimization algorithms, have been employed. However, existing techniques still struggle to balance both sampling time and diversity simultaneously. In response, HouseGanDi proposes a novel hybrid approach that amalgamates GANs and diffusion models to address the dual challenges of diversity and sampling time in floorplan generation. To the best of our knowledge, this work is the first to introduce a solution that not only balances sampling time and diversity but also enhances the realism of the generated floorplans. HouseGanDi is trained on the RPLAN dataset and combines the advantages of GANs and diffusion models in multimodal fashion while incorporating different techniques such as regularization methods and architectural modifications to optimize our objectives. The multimodality allows our model to jump a number of denoising steps while capturing data distributions. To evaluate the effect of the denoising step, we experimented with different time steps and found better diversity results at T = 20. Evaluation of diversity using FID demonstrates an average 15.5% improvement over the state-of-the-art houseDiffusion model, with a 41% reduction in generation time. However, challenges persist in generating non-orthogonal floorplans and accommodating intricate spatial layouts. |
| format | Article |
| id | doaj-art-4b05c25b5016437f9d9e58a6ef925d8f |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-4b05c25b5016437f9d9e58a6ef925d8f2025-08-20T03:19:12ZengIEEEIEEE Access2169-35362024-01-011212523512525210.1109/ACCESS.2024.345140610658971HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan GenerationAzmeraw Bekele Yenew0https://orcid.org/0009-0007-8524-2613Beakal Gizachew Assefa1https://orcid.org/0000-0001-9510-5216Elefelious Getachew Belay2https://orcid.org/0000-0001-8720-6295School of Information Technology and Engineering, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa, EthiopiaSchool of Information Technology and Engineering, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa, EthiopiaSchool of Information Technology and Engineering, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa, EthiopiaFloorplan synthesis is the process of generating new, realistic floor plans for buildings and homes using machine learning and generative models. In recent years, various generative methods, including GANs and diffusion models, have been utilized for the task of floorplan generation, demonstrating promising advancements in architectural design and planning. However, despite their potential, these methods face unique challenges like mode collapse, training instability, and sampling time, which require innovative solutions to overcome for further progress in this field. To address these issues, various techniques such as regualrization techniques, architectural modifications, and optimization algorithms, have been employed. However, existing techniques still struggle to balance both sampling time and diversity simultaneously. In response, HouseGanDi proposes a novel hybrid approach that amalgamates GANs and diffusion models to address the dual challenges of diversity and sampling time in floorplan generation. To the best of our knowledge, this work is the first to introduce a solution that not only balances sampling time and diversity but also enhances the realism of the generated floorplans. HouseGanDi is trained on the RPLAN dataset and combines the advantages of GANs and diffusion models in multimodal fashion while incorporating different techniques such as regularization methods and architectural modifications to optimize our objectives. The multimodality allows our model to jump a number of denoising steps while capturing data distributions. To evaluate the effect of the denoising step, we experimented with different time steps and found better diversity results at T = 20. Evaluation of diversity using FID demonstrates an average 15.5% improvement over the state-of-the-art houseDiffusion model, with a 41% reduction in generation time. However, challenges persist in generating non-orthogonal floorplans and accommodating intricate spatial layouts.https://ieeexplore.ieee.org/document/10658971/Diffusion modeldiversityfloorplanGANsampling time |
| spellingShingle | Azmeraw Bekele Yenew Beakal Gizachew Assefa Elefelious Getachew Belay HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation IEEE Access Diffusion model diversity floorplan GAN sampling time |
| title | HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation |
| title_full | HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation |
| title_fullStr | HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation |
| title_full_unstemmed | HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation |
| title_short | HouseGanDi: A Hybrid Approach to Strike a Balance of Sampling Time and Diversity in Floorplan Generation |
| title_sort | housegandi a hybrid approach to strike a balance of sampling time and diversity in floorplan generation |
| topic | Diffusion model diversity floorplan GAN sampling time |
| url | https://ieeexplore.ieee.org/document/10658971/ |
| work_keys_str_mv | AT azmerawbekeleyenew housegandiahybridapproachtostrikeabalanceofsamplingtimeanddiversityinfloorplangeneration AT beakalgizachewassefa housegandiahybridapproachtostrikeabalanceofsamplingtimeanddiversityinfloorplangeneration AT elefeliousgetachewbelay housegandiahybridapproachtostrikeabalanceofsamplingtimeanddiversityinfloorplangeneration |