Glass supercharges smartphone cameras with AI – except for hallucinations

Your phone’s camera is as much hardware as it is software, and Glass is hoping to improve both. but while this Wild Anamorphic Lens Moving to the market, the company (running on $9.3 million in new capital) has released an AI-powered camera upgrade that it says significantly improves image quality – without any awkward AI upscaling. Of artefacts.

GlassAI is an entirely software approach to enhancing images, using what they call a Neural Image Signal Processor (ISP). ISPs basically take raw sensor output – often flat, noisy and distorted – and turn it into the sharp, colorful images we see.

ISP is also becoming increasingly complex, as phone makers like Apple and Google like to synthesize multiple exposures, instantly detect and sharpen faces, make adjustments to small movements, and so on. And while many involve some form of machine learning or AI, they have to be careful: Using AI to generate descriptions may produce hallucinations or artifacts as the system tries to create visual information where none exists. . Such “super-resolution” models are useful in their place, but they have to be monitored carefully.

Glass builds both a full camera system and an ISP to back it up, based on an unusual lozenge-shaped front element. And while the former is working towards a market presence with some upcoming devices, the latter, it turns out, is a product worth selling in its own right.

“Our restoration networks correct optical aberrations and sensor issues while efficiently removing noise, and outperform traditional image signal processing pipelines in fine texture recovery,” CTO and co-founder Tom Bishop explains in his news release. “

Concept animation showing the process of going from RAW to glass-processed images.

The word “recovery” is important, because details are not created just like that. take out,

Read Complete News ➤

Benefits of eating guava for Americans