AMD files possible patent for NVIDIA DLSS alternative called Gaming Super Resolution
The US Patent Applications Office shows a new AMD patent with might be their alternative to NVIDIA's DLSS. It was filed under the name Gaming Super Resolution (GSR)”, and that logically would be the artist formerly known as FidelityFX Super Resolution (FSR).
One of the big features lacking on the current Radeon RX 6000 lineup is the lack of some sort of DLSS alternative that can really boost performance, especially in raytracing. it seems AMD is now hard at work at the tech, however it would be a way different implementation than DLSS running over its Tensor cores (AMD does not have any dedicated hardware for this in their GPUs). The patent entry however describes how it works. GSR would rely on interference to scale images. Additionally, AMD engineers claim that conventional neural networks are generalizable and are trained to operate without significant knowledge of the immediate problem. The company also claimed that this deep learning approach does not take into account aspects of the original image, which can cause colors or details to be lost in the final image. Their new solution would.
AMD's answer uses linear and non-linear upscaling technology, the combination will preserve and improve the accuracy of the image. It is also said that the technology will “create high-quality image approximations and achieve high framerates”.
“The GSR architecture employs image condensation and a combination of linear and non-linear operations to accelerate the process to levels viable for gaming. GSR renders images at a low-quality scale to create high-quality image approximations and achieve high frame rates.
High-quality reference images are approximated by applying a specific configuration of convolutional layers and trigger functions to a low-quality reference image. The GSR network approaches more generalized problems with greater precision and efficiency than conventional super-resolution techniques, training the weights of the convolutional layers with a corpus of images ”. For the moment we'll have to do with this leaked patent info. This new feature might be out for a while as it sounds like software houses will need to implement support for the technology as well.
The patent was submitted in November 2019 and was public earlier this week.
Senior Member
Posts: 163
Joined: 2017-08-31
I concur. The corpus of the explanation is more condensed and non-linear than conventional explanations.
Senior Member
Posts: 160
Joined: 2015-08-13
Filed in 2019 they have been hard at work good luck hope it levels the field
Member
Posts: 50
Joined: 2019-12-26
I find the condensation of images on my spectacles is filtering out precisely what layers I thought I was supposed to be condensing.
Senior Member
Posts: 1962
Joined: 2013-06-04
If only RX6000 and above cards can use it, damn. Hopefully at least RX5000 cards can use it too, people really need this to uplift performance and extend hardware life.
Senior Member
Posts: 3288
Joined: 2013-03-10
With my level of understanding the convolutions in that description made sure I couldn't get even an approximation of the general idea behind the technique.