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

The goal of this paper is to compare surface-based and volumetric 3D objectshape representations, as well as viewer-centered and object-centered referenceframes for single-view 3D shape prediction. We propose a new algorithm forpredicting depth maps from multiple viewpoints, with a single depth or RGBimage as input. By modifying the network and the way models are evaluated, wecan directly compare the merits of voxels vs. surfaces and viewer-centered vs.object-centered for familiar vs. unfamiliar objects, as predicted from RGB ordepth images. Among our findings, we show that surface-based methods outperformvoxel representations for objects from novel classes and produce higherresolution outputs. We also find that using viewer-centered coordinates isadvantageous for novel objects, while object-centered representations arebetter for more familiar objects. Interestingly, the coordinate framesignificantly affects the shape representation learned, with object-centeredplacing more importance on implicitly recognizing the object category andviewer-centered producing shape representations with less dependence oncategory recognition.

Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction