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 propose a method to allow precise and extremely fast mesh extraction from3D Gaussian Splatting. Gaussian Splatting has recently become very popular asit yields realistic rendering while being significantly faster to train thanNeRFs. It is however challenging to extract a mesh from the millions of tiny 3Dgaussians as these gaussians tend to be unorganized after optimization and nomethod has been proposed so far. Our first key contribution is a regularizationterm that encourages the gaussians to align well with the surface of the scene.We then introduce a method that exploits this alignment to extract a mesh fromthe Gaussians using Poisson reconstruction, which is fast, scalable, andpreserves details, in contrast to the Marching Cubes algorithm usually appliedto extract meshes from Neural SDFs. Finally, we introduce an optionalrefinement strategy that binds gaussians to the surface of the mesh, andjointly optimizes these Gaussians and the mesh through Gaussian splattingrendering. This enables easy editing, sculpting, rigging, animating,compositing and relighting of the Gaussians using traditional softwares bymanipulating the mesh instead of the gaussians themselves. Retrieving such aneditable mesh for realistic rendering is done within minutes with our method,compared to hours with the state-of-the-art methods on neural SDFs, whileproviding a better rendering quality. Our project page is the following:https://anttwo.github.io/sugar/

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering