EUVIMEDEUVIMED entdecken
Crossref

fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence

Francis Williams, Jiahui Huang, Jonathan Swartz, Gergely Klar, Vijay Thakkar, Matthew Cong, Xuanchi Ren, Ruilong Li, Clement Fuji-Tsang, Sanja Fidler, Eftychios Sifakis, Ken Museth

ACM Transactions on Graphics · 19.07.2024 · 43 (4) · 1-15

DOI: 10.1145/3658226 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.07.2024. Verfasst von Francis Williams und 11 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present f VDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. f VDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution, pooling, attention, ray-tracing, meshing, etc. f VDB simultaneously provides a much larger feature set (primitives and operators) than established frameworks with no loss in efficiency: our operators match or exceed the performance of other frameworks with narrower scope. Furthermore, f VDB can process datasets with much larger footprint and spatial resolution than prior works, while providing a competitive memory footprint on small inputs. To achieve this combination of versatility and performance, f VDB relies on a single novel VDB index grid acceleration structure paired with several key innovations including GPU accelerated sparse grid construction, convolution using tensorcores, fast ray tracing kernels using a Hierarchical Digital Differential Analyzer algorithm (HDDA), and jagged tensors. Our framework is fully integrated with PyTorch enabling interoperability with existing pipelines, and we demonstrate its effectiveness on a number of representative tasks such as large-scale point-cloud segmentation, high resolution 3D generative modeling, unbounded scale Neural Radiance Fields, and large-scale point cloud reconstruction.

Zitieren

APA

Williams, F., Huang, J., Swartz, J., Klar, G., Thakkar, V., Cong, M., Ren, X., Li, R., Fuji-Tsang, C., Fidler, S., Sifakis, E., & Museth, K. (2024). fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence. ACM Transactions on Graphics, 43(4), 1-15. https://doi.org/10.1145/3658226

Vancouver

Williams F, Huang J, Swartz J, Klar G, Thakkar V, Cong M, et al. fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence. ACM Transactions on Graphics. 2024;43(4):1-15. doi:10.1145/3658226

BibTeX
@article{Williams2024,
  author = {Williams, Francis and Huang, Jiahui and Swartz, Jonathan and Klar, Gergely and Thakkar, Vijay and Cong, Matthew and Ren, Xuanchi and Li, Ruilong and Fuji-Tsang, Clement and Fidler, Sanja and Sifakis, Eftychios and Museth, Ken},
  title = {fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence},
  journal = {ACM Transactions on Graphics},
  year = {2024},
  volume = {43},
  number = {4},
  pages = {1--15},
  doi = {10.1145/3658226}
}
Kostenlos starten →