Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions

Aleksandr Kolomeitsev, Anh-Huy Phan
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31249-31274, 2025.

Abstract

Topology optimization plays a crucial role in designing efficient and manufacturable structures. Traditional methods often yield free-form voids that, although providing design flexibility, introduce significant manufacturing challenges and require extensive post-processing. Conversely, feature-mapping topology optimization reduces post-processing efforts by constructing topologies using predefined geometric features. Nevertheless, existing approaches are significantly constrained by the limited set of geometric features available, the variety of parameters that each type of geometric feature can possess, and the necessity of employing differentiable signed distance functions. In this paper, we present a novel method that combines Neural Heaviside Signed Distance Functions (Heaviside SDFs) with structured latent shape representations to generate manufacturable voids directly within the optimization framework. Our architecture incorporates encoder and decoder networks to effectively approximate the Heaviside function and facilitate optimization within a unified latent space, thus addressing the feature diversity limitations of current feature-mapping techniques. Experimental results validate the effectiveness of our approach in balancing structural compliance, offering a new pathway to CAD-integrated design with minimal human intervention.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-kolomeitsev25a, title = {Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions}, author = {Kolomeitsev, Aleksandr and Phan, Anh-Huy}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {31249--31274}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/kolomeitsev25a/kolomeitsev25a.pdf}, url = {https://proceedings.mlr.press/v267/kolomeitsev25a.html}, abstract = {Topology optimization plays a crucial role in designing efficient and manufacturable structures. Traditional methods often yield free-form voids that, although providing design flexibility, introduce significant manufacturing challenges and require extensive post-processing. Conversely, feature-mapping topology optimization reduces post-processing efforts by constructing topologies using predefined geometric features. Nevertheless, existing approaches are significantly constrained by the limited set of geometric features available, the variety of parameters that each type of geometric feature can possess, and the necessity of employing differentiable signed distance functions. In this paper, we present a novel method that combines Neural Heaviside Signed Distance Functions (Heaviside SDFs) with structured latent shape representations to generate manufacturable voids directly within the optimization framework. Our architecture incorporates encoder and decoder networks to effectively approximate the Heaviside function and facilitate optimization within a unified latent space, thus addressing the feature diversity limitations of current feature-mapping techniques. Experimental results validate the effectiveness of our approach in balancing structural compliance, offering a new pathway to CAD-integrated design with minimal human intervention.} }
Endnote
%0 Conference Paper %T Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions %A Aleksandr Kolomeitsev %A Anh-Huy Phan %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-kolomeitsev25a %I PMLR %P 31249--31274 %U https://proceedings.mlr.press/v267/kolomeitsev25a.html %V 267 %X Topology optimization plays a crucial role in designing efficient and manufacturable structures. Traditional methods often yield free-form voids that, although providing design flexibility, introduce significant manufacturing challenges and require extensive post-processing. Conversely, feature-mapping topology optimization reduces post-processing efforts by constructing topologies using predefined geometric features. Nevertheless, existing approaches are significantly constrained by the limited set of geometric features available, the variety of parameters that each type of geometric feature can possess, and the necessity of employing differentiable signed distance functions. In this paper, we present a novel method that combines Neural Heaviside Signed Distance Functions (Heaviside SDFs) with structured latent shape representations to generate manufacturable voids directly within the optimization framework. Our architecture incorporates encoder and decoder networks to effectively approximate the Heaviside function and facilitate optimization within a unified latent space, thus addressing the feature diversity limitations of current feature-mapping techniques. Experimental results validate the effectiveness of our approach in balancing structural compliance, offering a new pathway to CAD-integrated design with minimal human intervention.
APA
Kolomeitsev, A. & Phan, A.. (2025). Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:31249-31274 Available from https://proceedings.mlr.press/v267/kolomeitsev25a.html.

Related Material