Retrieval-Augmented Multi-Floor Building Image Generation

• Item type: SIG Technical Reports(1)
• 公開日: 2024-06-22
• タイトル: Retrieval-Augmented Multi-Floor Building Image Generation
• タイトル / 言語: en
• タイトル: Retrieval-Augmented Multi-Floor Building Image Generation
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: CG一般セッション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Japan Advanced Institute of Science and Technology
• 著者所属: Japan Advanced Institute of Science and Technology
• 著者所属: Japan Advanced Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Japan Advanced Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Japan Advanced Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Japan Advanced Institute of Science and Technology
• 著者名: Zhengyang, Wang; Hao, Jin; Haoran, Xie
• 著者名(英): Zhengyang, Wang; Hao, Jin; Haoran, Xie
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Demand for generating building images from text prompts grows, despite recent advances in diffusion models greatly enhancing image quality. The current generative models struggle with controlling the number of floors. To this end, we propose a retrieval-augmented framework for generating building images with provided floor count using a diffusion model. Initially, the text prompts with the provided floor count to retrieve the most suitable image from a building image database. Then, we adopted a multi-level structure detection algorithm to obtain a sketch from the matched image to ensure structural consistency. Finally, the building image with the desired floor count and style is generated by diffusion model, guided by the detected building sketch. Our proposed framework enables accurate control over the floor count in building image synthesis. We demonstrate the robustness and scalability of generating building images with a specific floor count from text prompts.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Demand for generating building images from text prompts grows, despite recent advances in diffusion models greatly enhancing image quality. The current generative models struggle with controlling the number of floors. To this end, we propose a retrieval-augmented framework for generating building images with provided floor count using a diffusion model. Initially, the text prompts with the provided floor count to retrieve the most suitable image from a building image database. Then, we adopted a multi-level structure detection algorithm to obtain a sketch from the matched image to ensure structural consistency. Finally, the building image with the desired floor count and style is generated by diffusion model, guided by the detected building sketch. Our proposed framework enables accurate control over the floor count in building image synthesis. We demonstrate the robustness and scalability of generating building images with a specific floor count from text prompts.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10100541
• 書誌情報: 研究報告コンピュータグラフィックスとビジュアル情報学（CG）; 巻 2024-CG-194, 号 3, p. 1-4, 発行日 2024-06-22
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8949
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会