Artomatix CTO Clarifies Comments On PS4 Pro’s 4K Checkerboarding, Talks ‘Neural Network Upscaling’
“I can’t argue with Sony’s logic.”
The CTO of Artomatix, Eric Risser, recently shared his opinion on the PS4 Pro, and its checkerboard upscaling technique to deliver 4K images, exclusively with GamingBolt. His verdict was that while the PS4 Pro is an impressive machine, he was a bit disappointed at Sony choosing to go with a relatively simplistic upscaling technique like checkerboard rendering.
In a follow up statement to GamingBolt, however, Risser clarified his stance, noting that Sony choosing checkerboard rendering makes sense- it just disappoints him a little from a tech perspective.
“Although the nerd in me is a little disappointed, I can’t argue with Sony’s logic for going with a signal processing strategy, they’re reliable and safe, it’s what people have been doing for years. That said, I think in the long run, better quality and performance can be gained by using neural network upscaling,” he said.
“Here at Artomatix we’ve developed our upscaling technology for a slightly different application. Our focus is upscaling old game assets so they can be re-used in new games, rather than being re-made from scratch. For games like Tomb Raider as an example, the developers have invested a lot of time and money building a library of textures: tree-bark, rock, grass, etc. which they mostly have to abandon when moving to a new console generation that can handle higher resolution textures. The idea with our upscaling technology is to recycle those old assets for the next generation. Also, classic games like Ocarina of Time or Shadow of the Colossus could be remastered with better game art, not just rendered at a higher resolution.
“We’re also exploring our upscaling approach for old video footage. Imagine if the Simpsons from the early 90’s could be automatically re-synthesized to look like the latest season. I think the same idea could be used for console’s in the future. By using advanced real-time upscaling techniques, it should be possible to actually decrease the number of pixels that are currently being rendered, while getting higher resolution at a better visual quality. Our peers at Magic Pony Ltd. were working on a similar idea for utilizing neural network upscaling on streaming internet video, they were recently bought by Twitter for $150m.”
His idea certainly sounds exciting to me- especially the applications that he describes.
Thoughts on Eric’s clarification? Let us know in the comments section below.