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 CN-DHF (Compact Neural Double-Height-Field), a novel hybridneural implicit 3D shape representation that is dramatically more compact thanthe current state of the art. Our representation leverages Double-Height-Field(DHF) geometries, defined as closed shapes bounded by a pair of oppositelyoriented height-fields that share a common axis, and leverages the followingkey observations: DHFs can be compactly encoded as 2D neural implicits thatcapture the maximal and minimal heights along the DHF axis; and typical closed3D shapes are well represented as intersections of a very small number (threeor fewer) of DHFs. We represent input geometries as CNDHFs by first computingthe set of DHFs whose intersection well approximates each input shape, and thenencoding these DHFs via neural fields. Our approach delivers high-qualityreconstructions, and reduces the reconstruction error by a factor of 2:5 onaverage compared to the state-of-the-art, given the same parameter count orstorage capacity. Compared to the best-performing alternative, our methodproduced higher accuracy models on 94% of the 400 input shape and parametercount combinations tested.

CN-DHF: Compact Neural Double Height-Field Representations of 3D Shapes