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

To be robust to illumination changes when detecting objects in images, thecurrent trend is to train a Deep Network with training images captured undermany different lighting conditions. Unfortunately, creating such a training setis very cumbersome, or sometimes even impossible, for some applications such as3D pose estimation of specific objects, which is the application we focus on inthis paper. We therefore propose a novel illumination normalization method thatlets us learn to detect objects and estimate their 3D pose under challengingillumination conditions from very few training samples. Our key insight is thatnormalization parameters should adapt to the input image. In particular, werealized this via a Convolutional Neural Network trained to predict theparameters of a generalization of the Difference-of-Gaussians method. We showthat our method significantly outperforms standard normalization methods anddemonstrate it on two challenging 3D detection and pose estimation problems.

ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation