Title | ||
---|---|---|
Point2FFD: Learning Shape Representations of Simulation-Ready 3D Models for Engineering Design Optimization |
Abstract | ||
---|---|---|
Methods for learning on 3D point clouds became ubiquitous due to the popularization of 3D scanning technology and advances of machine learning techniques. Among these methods, point-based deep neural networks have been utilized to explore 3D designs in optimization tasks. However, engineering computer simulations require high-quality meshed models, which are challenging to automatically generate from unordered point clouds. In this work, we propose Point2FFD: A novel deep neural network for learning compact geometric representations and generating simulation-ready meshed models. Built upon an autoencoder architecture, Point2FFD learns to compress 3D point clouds into a latent design space, from which the network generates 3D polygonal meshes by selecting and deforming simulation-ready mesh templates. Through benchmark experiments, we show that our proposed network achieves comparable shape-generative performance than existing state-of-the-art point-based generative models. In real world-inspired vehicle aerodynamic optimizations, we demonstrate that Point2FFD generates simulation-ready meshes of realistic car shapes and leads to better optimized designs than the benchmarked networks. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/3DV53792.2021.00110 | 2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021) |
DocType | ISSN | Citations |
Conference | 2378-3826 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thiago Rios | 1 | 1 | 1.03 |
Bas van Stein | 2 | 17 | 8.47 |
Thomas Bäck | 3 | 629 | 86.94 |
Bernhard Sendhoff | 4 | 2272 | 240.31 |
Stefan Menzel | 5 | 67 | 16.25 |