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

Understanding the 3D world is a fundamental problem in computer vision.However, learning a good representation of 3D objects is still an open problemdue to the high dimensionality of the data and many factors of variationinvolved. In this work, we investigate the task of single-view 3D objectreconstruction from a learning agent's perspective. We formulate the learningprocess as an interaction between 3D and 2D representations and propose anencoder-decoder network with a novel projection loss defined by the perspectivetransformation. More importantly, the projection loss enables the unsupervisedlearning using 2D observation without explicit 3D supervision. We demonstratethe ability of the model in generating 3D volume from a single 2D image withthree sets of experiments: (1) learning from single-class objects; (2) learningfrom multi-class objects and (3) testing on novel object classes. Results showsuperior performance and better generalization ability for 3D objectreconstruction when the projection loss is involved.

Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision