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

While 3D shape representations enable powerful reasoning in many visual andperception applications, learning 3D shape priors tends to be constrained tothe specific categories trained on, leading to an inefficient learning process,particularly for general applications with unseen categories. Thus, we proposePatchComplete, which learns effective shape priors based on multi-resolutionlocal patches, which are often more general than full shapes (e.g., chairs andtables often both share legs) and thus enable geometric reasoning about unseenclass categories. To learn these shared substructures, we learnmulti-resolution patch priors across all train categories, which are thenassociated to input partial shape observations by attention across the patchpriors, and finally decoded into a complete shape reconstruction. Suchpatch-based priors avoid overfitting to specific train categories and enablereconstruction on entirely unseen categories at test time. We demonstrate theeffectiveness of our approach on synthetic ShapeNet data as well as challengingreal-scanned objects from ScanNet, which include noise and clutter, improvingover state of the art in novel-category shape completion by 19.3% in chamferdistance on ShapeNet, and 9.0% for ScanNet.

PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories