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 use of computer generated images to train Deep Neural Networks is aviable alternative to real images when the latter are scarce or expensive. Inthis paper, we study how the illumination model used by the rendering softwareaffects the quality of the generated images. We created eight training sets,each one with a different illumination model, and tested them on threedifferent network architectures, ResNet, U-Net and a combined architecturedeveloped by us. The test set consisted of photos of 3D printed objectsproduced from the same CAD models used to generate the training set. The effectof the other parameters of the rendering process, such as textures and cameraposition, was randomized.  Our results show that the effect of the illumination model is important,comparable in significance to the network architecture. We also show that bothlight probes capturing natural environmental light, and modelled lightingenvironments, can give good results. In the case of light probes, we identifiedas two significant factors affecting performance the similarity between thelight probe and the test environment, as well as the light probe's resolution.Regarding modelled lighting environment, similarity with the test environmentwas again identified as a significant factor.

A study of the effect of the illumination model on the generation of synthetic training datasets