Skip to main content

Neural Nets Give Low-End Phone Pics DSLR Look

Researchers have found a way to use neural networks to create DSLR-quality photos from snapshots taken with low-end smartphones. A team of scientists at the ETH Zurich Computer Vision Lab recently published a paper describing a deep learning approach that uses neural networks to translate photos taken by cameras with limited capabilities into DSLR-quality photos automatically. "We tackle this problem by introducing a weakly supervised photo enhancer -- a novel image-to-image GAN-based architecture," they wrote.

from TechNewsWorld http://ift.tt/2yjpMJv

Comments

Popular posts from this blog

Manifesto Hatched to Close Gap Between Business and IT

The BizOps Coalition hopes to bridge the gap between technology investments and business outcomes through an effort called the BizOps Manifesto. The BizOps movement has gained traction with leading organizations, helping them to better align IT with business outcomes. But more needs to be done. That led to the Manifesto's creation. from TechNewsWorld https://ift.tt/35oXxXx

Protecting Kids From Immersive Tech Could Lead to Over-Censorship

Attempts to protect children's safety in the two-dimensional realm of online social media could adversely impact the 3D world of augmented and virtual reality, according to a newly released report by a technology think tank. The post Protecting Kids From Immersive Tech Could Lead to Over-Censorship appeared first on TechNewsWorld . from TechNewsWorld https://ift.tt/iroRM6I

AI-Enhanced Next-Gen Smart Glasses Could Revolutionize Wearables

The 2014 Google Glass debacle stigmatized smart glasses, but the devices may be poised for a comeback. Despite the failure of Google Glass, Meta and Google appear to be all in on the next generation of smart glasses that combine fashion, functionality, and generative AI into a compelling form factor. The post AI-Enhanced Next-Gen Smart Glasses Could Revolutionize Wearables appeared first on TechNewsWorld . from TechNewsWorld https://ift.tt/taJAubh