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 photometric stereo (PS) problem consists in reconstructing the 3D-surfaceof an object, thanks to a set of photographs taken under different lightingdirections. In this paper, we propose a multi-scale architecture for PS which,combined with a new dataset, yields state-of-the-art results. Our proposedarchitecture is flexible: it permits to consider a variable number of images aswell as variable image size without loss of performance. In addition, we definea set of constraints to allow the generation of a relevant synthetic dataset totrain convolutional neural networks for the PS problem. Our proposed dataset ismuch larger than pre-existing ones, and contains many objects with challengingmaterials having anisotropic reflectance (e.g. metals, glass). We show onpublicly available benchmarks that the combination of both these contributionsdrastically improves the accuracy of the estimated normal field, in comparisonwith previous state-of-the-art methods.

MS-PS: A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataset