SoylentNews is people
SoylentNews
from the making-a-mountain-out-of-a-mole-hill dept.
Neural SuperSampling Is a Hardware Agnostic DLSS Alternative by Facebook
A new paper published by Facebook researchers just ahead of SIGGRAPH 2020 introduces neural supersampling, a machine learning-based upsampling approach not too dissimilar from NVIDIA's Deep Learning Super Sampling. However, neural supersampling does not require any proprietary hardware or software to run and its results are quite impressive as you can see in the example images, with researchers comparing them to the quality we've come to expect from DLSS.
Video examples on Facebook's blog post.
The researchers use some extremely low-fi upscales to make their point, but you could also imagine scaling from a resolution like 1080p straight to 8K. Upscaling could be combined with eye tracking and foveated rendering to reduce rendering times even further.
Also at UploadVR and VentureBeat.
Journal Reference:
Lei Xiao, Salah Nouri, Matt Chapman, Alexander Fix, Douglas Lanman, Anton Kaplanyan,Neural Supersampling for Real-time Rendering - Facebook Research, (DOI: https://research.fb.com/publications/neural-supersampling-for-real-time-rendering/)
Related: With Google's RAISR, Images Can be Up to 75% Smaller Without Losing Detail
Nvidia's Turing GPU Pricing and Performance "Poorly Received"
HD Emulation Mod Makes "Mode 7" SNES Games Look Like New
Neural Networks Upscale Film From 1896 to 4K, Make It Look Like It Was Shot on a Modern Smartphone
Apple Goes on an Acquisition Spree, Turns Attention to NextVR
(Score: 0) by Anonymous Coward on Saturday July 04 2020, @03:35PM (4 children)
Great, now you can try to blur out people you want unrecognizable and it'll bloody well undo that blur... Thanks In-q-tel...
(Score: 2) by takyon on Saturday July 04 2020, @03:43PM (2 children)
If you want to make people unrecognizable, you need to cover them up with a single solid color.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Saturday July 04 2020, @03:55PM
>> you need to cover them up with a single solid color.
But not black, which AI trained on current datasets recognizes as criminal.
(Score: 1) by anubi on Saturday July 04 2020, @11:25PM
Cut and paste a blur from someone else. Public figures.
"Prove all things; hold fast that which is good." [KJV: I Thessalonians 5:21]
(Score: 2) by rleigh on Sunday July 05 2020, @10:07AM
You can do that without any machine learning (within certain limits). All the blurring has done is spread out the signal over a wide range of pixels. It doesn't take much effort to gather it back in. Running a convolution kernel over the blurred region is often sufficient to reconstruct a very close approximation to the original.