SCAPE:利用进化搜索概念性建筑提示
SCAPE: Searching Conceptual Architecture Prompts using Evolution
AI总结:
SCAPE 将进化算法与 GPT-4 生成式 AI 结合,通过文本变异和交叉搜索概念性建筑提示,相比 DALL-E 3 显著提升图像新颖性、质量和探索效率。
摘要:
概念性建筑涉及对新想法的高度创造性探索,这些想法通常来自其他学科,因为建筑师会考虑建筑的全新形式、材料、纹理和颜色。尽管当今的生成式人工智能系统能够产生卓越的结果,但它们缺乏进化算法数十年来所展现的创造力。我们提出的工具 SCAPE 将进化搜索与生成式人工智能相结合,使用户能够通过简单的点击式界面,探索受其初始输入启发的、富有创意且质量良好的设计。SCAPE 向生成式人工智能中注入随机性,并实现记忆功能,利用 GPT-4 内置的语言能力,通过基于文本的变异和交叉来改变提示。我们证明,与 DALL-E 3 相比,SCAPE 使图像新颖性提高了 67%,同时在质量和易用性方面也有所提升;我们表明,仅经过三次迭代,SCAPE 的图像新颖性就提高了 24%,从而实现了有效探索,以及用户对图像的优化。我们邀请了 20 多位独立建筑师对 SCAPE 进行评估,他们给出了显著积极的反馈。
英文摘要:
Conceptual architecture involves a highly creative exploration of novel ideas, often taken from other disciplines as architects consider radical new forms, materials, textures and colors for buildings. While today's generative AI systems can produce remarkable results, they lack the creativity demonstrated for decades by evolutionary algorithms. SCAPE, our proposed tool, combines evolutionary search with generative AI, enabling users to explore creative and good quality designs inspired by their initial input through a simple point and click interface. SCAPE injects randomness into generative AI, and enables memory, making use of the built-in language skills of GPT-4 to vary prompts via text-based mutation and crossover. We demonstrate that compared to DALL-E 3, SCAPE enables a 67% improvement in image novelty, plus improvements in quality and effectiveness of use; we show that in just three iterations SCAPE has a 24% image novelty increase enabling effective exploration, plus optimization of images by users. We use more than 20 independent architects to assess SCAPE, who provide markedly positive feedback.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。