DeepWheel
收藏资源简介:
DeepWheel数据集是由韩国科学技术院(KAIST)的研究团队创建的,包含超过6,000张逼真的合成渲染图像和904个经过有限元分析(FEA)的结构分析3D模型。该数据集利用生成式AI技术生成2D渲染图像,并通过深度估计重建3D几何形状,进而进行结构仿真以提取工程性能数据。数据集广泛应用于代理模型训练、数据驱动逆设计以及设计空间探索等领域,为车辆轮设计提供了宝贵资源。
The DeepWheel dataset was developed by a research team from the Korea Advanced Institute of Science and Technology (KAIST). It contains over 6,000 photorealistic synthetic rendered images and 904 3D structural analysis models that have undergone finite element analysis (FEA). This dataset leverages generative AI technologies to generate 2D rendered images, reconstructs 3D geometric shapes via depth estimation, and conducts structural simulations to extract engineering performance data. The dataset is widely applied in fields such as surrogate model training, data-driven inverse design and design space exploration, serving as a valuable resource for vehicle wheel design.

- 1DeepWheel: Generating a 3D Synthetic Wheel Dataset for Design and Performance Evaluation韩国科学技术院(KAIST) · 2025年



