Thursday, May 17, 2018

Machine Learning to Reduce High-ISO Noise

MSN, DPReview: Machine learning is often presented as a tool to improve high-ISO. Intel and the University of Illinois Urbana-Champlain are to present their AI algorithm in June:

"The Intel and UIUC team claims the algorithm can now amplify low-light images the equivalent of up to 300 times the exposure, without the same noise and discoloration that programs like Photoshop might introduce or having to take two separate images."



Imaging Resource publishes an interview with Sony managers called "A.I. is the future of mirrorless cameras:"

"That kind of technology is improving very fast. For example, our current processor has some general computing unit, but maybe in the next generation, the general computing CPU should become more designed for AI."

In a half-year old video, Sony Teruo Hirayama and Sony’s strategic advisor also the director of the MIT Media Lab, Joichi Ito discuss how image sensors and AI will combine to enhance human capabilities and open up new possibilities in the future:

No comments:

Post a Comment

All comments are moderated to avoid spam and personal attacks.