AMD FSR antialiasing discussion

Since it's upscaling, it should be called subresolution.

Cheers

 

What methods do they imply they are using?

 

They talk about neural network resolution, they use AI like DLSS if I understand well

 

[0008] and [0009] made it unclear to me since they specifically talk about the problems with deep learning and other generalized ML approaches. They also mention a wholly learned environment. Curious to know if/how this differs from DLSS in practice. AMD GPUs don't have nearly the matrix math capability of Nvidia GPUs. But I also don't know if that is the bottleneck for DLSS performance.

 

But they spoke of training after. The problem with the current method is not taking into account the non linear information.

EDIT: This is in RDNA 3 speculation but AMD told it will be available for RDNA 2 GPU, Xbox Series and PS5. Maybe it will work with RDNA 1 GPU too?

 

Too bad consoles missed this one.

 

https://www.techradar.com/news/amd-...could-boost-ps5-and-xbox-series-x-performance

Wrong it could work on Nvidia GPU too

https://www.pcgamer.com/even-nvidia...enefit-from-amds-fidelityfx-super-resolution/

They want the solution to be fully cross platform.

 

RNNs are heavy and store state in weights, there is no need in storing state in weights if you can feed it explicitly, i.e. feed 2 consequent frames to CNN at once.
It seems the thing described in the patent is just spatial upscaler, so there must be temporal part as well otherwise it wouldn't be able to converrge to higher res like DLSS does.

 

I don't think this is a useful way of thinking about RNNs, after all there is generally nothing preventing you from passing past inputs to the network. It's crucial that the RNN state is a learned distilled representation of significant features encountered in the recent past, you don't want to recalculate that from scratch every frame.

 

RNNs learn probability of the next event based on previous via the hidden state, there is no need for this in temporal image processing because two consequent frames are being explicitly aligned with motion vectors, so you would get nothing from RNN.

 

Of cause they are, nobody argues about that.

Why would you want RNN for something like this?
Уou can simply store the previously upscaled high res images, warp it via motion vectors and then combine it with current low res image, that's how TAAU works.

That's irrelevant for gaming. In video you don't have precise motion vectors, just a mere approximation - optical flow, on the other hand, there are no such time constrains for video processing as in gaming, so you can brute force some problems by throwing more math at it.
Other than this, RNNs would not help getting additional details. It's camera jittering that is adding individual details into every frame in games, it has nothing to do with RNNs.

 

The patent is from 2019 though. I have doubts about it being relevant to FSR.

 

Oh well i ment a solution akin to DLSS/tensor cores. Anyway, as pointed out by DegustatoR, this isnt anything official anyways, but perfect for a RDNA3 speculation discussion though.

 

Idk.
Rename DLSS thread into DLSS + FSR and paste all discussion there?

No shit.
Stuff takes time to get outta the oven.

Every time.

AMD isn't bolting MFMA engines to client GPUs.

This has no relation to RDNA3 at all.
Not that the latter needs upscaling techniques at large.