Point2FFD: learning shape representations of simulation-ready 3D models for engineering design optimization

Thiago Rios, Bas Van Stein, Thomas Bäck, Bernhard Sendhoff, Stefan Menzel

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 languageEnglish
Title of host publication2021 International Conference on 3D Vision (3DV)
Number of pages10
ISBN (Electronic)9781665426886
ISBN (Print)9781665426893 (PoD)
Publication statusPublished - 6 Jan 2022
Externally publishedYes
Event2021 International Conference on 3D Vision (3DV) - London, United Kingdom
Duration: 1 Dec 20213 Dec 2021

Publication series

NameInternational Conference on 3D Vision proceedings
ISSN (Print)2378-3826
ISSN (Electronic)2475-7888


Conference2021 International Conference on 3D Vision (3DV)

Bibliographical note

Publisher Copyright: © 2021 IEEE
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE)


  • Point cloud compression
  • Deep learning
  • Solid modeling
  • Three-dimensional displays
  • Shape
  • Neural networks
  • Lattices


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.

Cite this