论文标题
3DALL-E：在3D设计工作流程中整合文本对图像AI
3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows
论文作者
论文摘要
文本到图像AI能够为灵感生成新颖的图像，但是他们在3D设计工作流程中的应用以及设计师如何使用AI-提供的灵感来构建3D模型。为了调查这一点，我们将DALL-E，GPT-3和剪辑集成了3DALL-E的CAD软件，该插件为3D设计生成了2D Image Inspiration。 3DALL-E允许用户根据其建模的内容来构建文本和图像提示。在与13位设计师的一项研究中，我们发现设计师在工作流程中看到了3DALL-E中的巨大潜力，并且可以使用文本对图像AI来制作参考图像，防止设计固定并激发灵感设计考虑因素。我们详细介绍了在3D建模任务中观察到的提示模式，并提供了在参与者之间观察到的迅速复杂性的度量。根据我们的发现，我们讨论了3DALL-E如何与现有的生成设计工作流合并，并提出及时的书目作为人类设计历史的一种形式。
Text-to-image AI are capable of generating novel images for inspiration, but their applications for 3D design workflows and how designers can build 3D models using AI-provided inspiration have not yet been explored. To investigate this, we integrated DALL-E, GPT-3, and CLIP within a CAD software in 3DALL-E, a plugin that generates 2D image inspiration for 3D design. 3DALL-E allows users to construct text and image prompts based on what they are modeling. In a study with 13 designers, we found that designers saw great potential in 3DALL-E within their workflows and could use text-to-image AI to produce reference images, prevent design fixation, and inspire design considerations. We elaborate on prompting patterns observed across 3D modeling tasks and provide measures of prompt complexity observed across participants. From our findings, we discuss how 3DALL-E can merge with existing generative design workflows and propose prompt bibliographies as a form of human-AI design history.
