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

Implicit surface representations, such as signed-distance functions, combinedwith deep learning have led to impressive models which can represent detailedshapes of objects with arbitrary topology. Since a continuous function islearned, the reconstructions can also be extracted at any arbitrary resolution.However, large datasets such as ShapeNet are required to train such models. Inthis paper, we present a new mid-level patch-based surface representation. Atthe level of patches, objects across different categories share similarities,which leads to more generalizable models. We then introduce a novel method tolearn this patch-based representation in a canonical space, such that it is asobject-agnostic as possible. We show that our representation trained on onecategory of objects from ShapeNet can also well represent detailed shapes fromany other category. In addition, it can be trained using much fewer shapes,compared to existing approaches. We show several applications of our newrepresentation, including shape interpolation and partial point cloudcompletion. Due to explicit control over positions, orientations and scales ofpatches, our representation is also more controllable compared to object-levelrepresentations, which enables us to deform encoded shapes non-rigidly.

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations