EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

Biao Zhang, Jiapeng Tang, Matthias Nießner, Peter Wonka

ACM Transactions on Graphics · 2023-08 · 42 (4) · 1-16

DOI: 10.1145/3592442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 26.07.2023. Verfasst von Biao Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 220-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents them as neural fields. The concept of neural fields has previously been combined with a global latent vector, a regular grid of latent vectors, or an irregular grid of latent vectors. Our new representation encodes neural fields on top of a set of vectors. We draw from multiple concepts, such as the radial basis function representation, and the cross attention and self-attention function, to design a learnable representation that is especially suitable for processing with transformers. Our results show improved performance in 3D shape encoding and 3D shape generative modeling tasks. We demonstrate a wide variety of generative applications: unconditioned generation, category-conditioned generation, text-conditioned generation, point-cloud completion, and image-conditioned generation. Code: https://1zb.github.io/3DShape2VecSet/.

Zitieren

APA

Zhang, B., Tang, J., Nießner, M., & Wonka, P. (2023). 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models. ACM Transactions on Graphics, 42(4), 1-16. https://doi.org/10.1145/3592442

Vancouver

Zhang B, Tang J, Nießner M, Wonka P. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models. ACM Transactions on Graphics. 2023;42(4):1-16. doi:10.1145/3592442

BibTeX
@article{Zhang2023,
  author = {Zhang, Biao and Tang, Jiapeng and Nießner, Matthias and Wonka, Peter},
  title = {3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models},
  journal = {ACM Transactions on Graphics},
  year = {2023},
  volume = {42},
  number = {4},
  pages = {1--16},
  doi = {10.1145/3592442}
}
Kostenlos starten →