English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce 3DShape2VecSet, a novel shape representation for neural fieldsdesigned for generative diffusion models. Our shape representation can encode3D shapes given as surface models or point clouds, and represents them asneural fields. The concept of neural fields has previously been combined with aglobal latent vector, a regular grid of latent vectors, or an irregular grid oflatent vectors. Our new representation encodes neural fields on top of a set ofvectors. We draw from multiple concepts, such as the radial basis functionrepresentation and the cross attention and self-attention function, to design alearnable representation that is especially suitable for processing withtransformers. Our results show improved performance in 3D shape encoding and 3Dshape generative modeling tasks. We demonstrate a wide variety of generativeapplications: unconditioned generation, category-conditioned generation,text-conditioned generation, point-cloud completion, and image-conditionedgeneration.

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