Component Segmentation of Engineering Drawings Using Graph Convolutional Networks

no code implementations • 1 Dec 2022 • Wentai Zhang, Joe Joseph, Yue Yin, Liuyue Xie, Tomotake Furuhata, Soji Yamakawa, Kenji Shimada, Levent Burak Kara

We test our framework in the context of semantic segmentation of text, dimension and, contour components in engineering drawings.

Segmentation Semantic Segmentation

3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders

no code implementations • 16 Apr 2019 • Wentai Zhang, Zhangsihao Yang, Haoliang Jiang, Suyash Nigam, Soji Yamakawa, Tomotake Furuhata, Kenji Shimada, Levent Burak Kara

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs.

3D Shape Representation

Data-driven Upsampling of Point Clouds

no code implementations • 8 Jul 2018 • Wentai Zhang, Haoliang Jiang, Zhangsihao Yang, Soji Yamakawa, Kenji Shimada, Levent Burak Kara

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis.