Projects per year
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.
Original language | English |
---|---|
Title of host publication | 2021 International Conference on 3D Vision (3DV) |
Publisher | IEEE |
Pages | 1024-1033 |
Number of pages | 10 |
ISBN (Electronic) | 9781665426886 |
ISBN (Print) | 9781665426893 (PoD) |
DOIs | |
Publication status | Published - 6 Jan 2022 |
Externally published | Yes |
Event | 2021 International Conference on 3D Vision (3DV) - London, United Kingdom Duration: 1 Dec 2021 → 3 Dec 2021 |
Publication series
Name | International Conference on 3D Vision proceedings |
---|---|
Publisher | IEEE |
ISSN (Print) | 2378-3826 |
ISSN (Electronic) | 2475-7888 |
Conference
Conference | 2021 International Conference on 3D Vision (3DV) |
---|---|
Period | 1/12/21 → 3/12/21 |
Bibliographical note
Publisher Copyright: © 2021 IEEEThis project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE)
Keywords
- Point cloud compression
- Deep learning
- Solid modeling
- Three-dimensional displays
- Shape
- Neural networks
- Lattices
Fingerprint
Dive into the research topics of 'Point2FFD: learning shape representations of simulation-ready 3D models for engineering design optimization'. Together they form a unique fingerprint.Projects
- 1 Finished
-
H2020_ITN_ECOLE_Coordinator
European Commission - Management Costs, European Commission
1/04/18 → 31/03/22
Project: Research