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 present ShapeClipper, a novel method that reconstructs 3D object shapesfrom real-world single-view RGB images. Instead of relying on laborious 3D,multi-view or camera pose annotation, ShapeClipper learns shape reconstructionfrom a set of single-view segmented images. The key idea is to facilitate shapelearning via CLIP-based shape consistency, where we encourage objects withsimilar CLIP encodings to share similar shapes. We also leverage off-the-shelfnormals as an additional geometric constraint so the model can learn betterbottom-up reasoning of detailed surface geometry. These two novel consistencyconstraints, when used to regularize our model, improve its ability to learnboth global shape structure and local geometric details. We evaluate our methodover three challenging real-world datasets, Pix3D, Pascal3D+, and OpenImages,where we achieve superior performance over state-of-the-art methods.

ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency