DeepWheel
收藏资源简介:
DeepWheel数据集是由韩国科学技术院(KAIST)的研究团队开发的一种合成三维车轮设计性能数据集。该数据集通过使用生成式人工智能技术生成超过6,000张逼真的合成渲染图像和904个经过有限元分析的结构分析三维模型组成的多模态数据集。它为代理模型训练、数据驱动的逆设计和设计空间探索提供了宝贵的资源。数据集在创意共享署名-非商业4.0国际许可下发布。
The DeepWheel dataset is a synthetic 3D wheel design performance dataset developed by a research team from the Korea Advanced Institute of Science and Technology (KAIST). This multimodal dataset is composed of over 6,000 photorealistic synthetic rendered images and 904 3D structural analysis models subjected to finite element analysis, all generated via generative artificial intelligence technologies. It serves as a valuable resource for surrogate model training, data-driven inverse design, and design space exploration. The dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International License.




