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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

3D reconstruction from a single RGB image is a challenging problem incomputer vision. Previous methods are usually solely data-driven, which lead toinaccurate 3D shape recovery and limited generalization capability. In thiswork, we focus on object-level 3D reconstruction and present a geometry-basedend-to-end deep learning framework that first detects the mirror plane ofreflection symmetry that commonly exists in man-made objects and then predictsdepth maps by finding the intra-image pixel-wise correspondence of thesymmetry. Our method fully utilizes the geometric cues from symmetry during thetest time by building plane-sweep cost volumes, a powerful tool that has beenused in multi-view stereopsis. To our knowledge, this is the first work thatuses the concept of cost volumes in the setting of single-image 3Dreconstruction. We conduct extensive experiments on the ShapeNet dataset andfind that our reconstruction method significantly outperforms the previousstate-of-the-art single-view 3D reconstruction networks in term of the accuracyof camera poses and depth maps, without requiring objects being completelysymmetric. Code is available at https://github.com/zhou13/symmetrynet.

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction