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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present Surf-D, a novel method for generating high-quality 3D shapes asSurfaces with arbitrary topologies using Diffusion models. Previous methodsexplored shape generation with different representations and they suffer fromlimited topologies and poor geometry details. To generate high-quality surfacesof arbitrary topologies, we use the Unsigned Distance Field (UDF) as oursurface representation to accommodate arbitrary topologies. Furthermore, wepropose a new pipeline that employs a point-based AutoEncoder to learn acompact and continuous latent space for accurately encoding UDF and supporthigh-resolution mesh extraction. We further show that our new pipelinesignificantly outperforms the prior approaches to learning the distance fields,such as the grid-based AutoEncoder, which is not scalable and incapable oflearning accurate UDF. In addition, we adopt a curriculum learning strategy toefficiently embed various surfaces. With the pretrained shape latent space, weemploy a latent diffusion model to acquire the distribution of various shapes.Extensive experiments are presented on using Surf-D for unconditionalgeneration, category conditional generation, image conditional generation, andtext-to-shape tasks. The experiments demonstrate the superior performance ofSurf-D in shape generation across multiple modalities as conditions. Visit ourproject page at https://yzmblog.github.io/projects/SurfD/.

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models