This paper introduces a public dataset of 1.4 million procedurally-generated
bicycle designs represented parametrically, as JSON files, and as rasterized
images. The dataset is created through the use of a rendering engine which
harnesses the BikeCAD software to generate vector graphics from parametric
designs. This rendering engine is discussed in the paper and also released
publicly alongside the dataset. Though this dataset has numerous applications,
a principal motivation is the need to train cross-modal predictive models
between parametric and image-based design representations. For example, we
demonstrate that a predictive model can be trained to accurately estimate
Contrastive Language-Image Pretraining (CLIP) embeddings from a parametric
representation directly. This allows similarity relations to be established
between parametric bicycle designs and text strings or reference images.
Trained predictive models are also made public. The dataset joins the BIKED
dataset family which includes thousands of mixed-representation human-designed
bicycle models and several datasets quantifying design performance. The code
and dataset can be found at:
this https URL

该论文介绍了一个公共数据集，其中包含了 140 万个以参数方式表示的、程序生成的自行车设计，以 JSON 文件和栅格化图像形式提供。该数据集的创建依赖于一个渲染引擎，该引擎利用 BikeCAD 软件从参数化设计生成矢量图形。论文讨论了这个渲染引擎，并与数据集一起公开发布。尽管该数据集有众多应用，主要动机之一是需要训练参数化和基于图像的设计表示之间的交叉模态预测模型。例如，我们演示了可以训练预测模型，直接从参数化表示准确估计 Contrastive Language-Image Pretraining (CLIP) 嵌入。这样可以建立参数化自行车设计与文本字符串或参考图像之间的相似性关系。已公开发布了训练好的预测模型。该数据集是 BIKED 数据集系列的一部分，包括数千个混合表示的人工设计自行车模型和几个量化设计性能的数据集。代码和数据集可以在 this https URL 找到。