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

Retrieving accurate 3D reconstructions of objects from the way they reflectlight is a very challenging task in computer vision. Despite more than fourdecades since the definition of the Photometric Stereo problem, most of theliterature has had limited success when global illumination effects such ascast shadows, self-reflections and ambient light come into play, especially forspecular surfaces.  Recent approaches have leveraged the power of deep learning in conjunctionwith computer graphics in order to cope with the need of a vast number oftraining data in order to invert the image irradiance equation and retrieve thegeometry of the object. However, rendering global illumination effects is aslow process which can limit the amount of training data that can be generated.  In this work we propose a novel pixel-wise training procedure for normalprediction by replacing the training data (observation maps) of globallyrendered images with independent per-pixel generated data. We show that globalphysical effects can be approximated on the observation map domain and thissimplifies and speeds up the data creation procedure.  Our network, PX-NET, achieves the state-of-the-art performance compared toother pixelwise methods on synthetic datasets, as well as the Diligent realdataset on both dense and sparse light settings.

PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks