WWDC25: Combine Metal 4 machine learning and graphics
Demonstrated a way to combine neural network in the graphics pipeline directly through the shaders, using an example of Texture Compression. However there is no mention of using which ML technique texture is compressed.
Can anyone point me to some well known model/s for this particular use case shown in WWDC25.
There isn't a publicly available model associated with this talk.
However, there is literature that outlines a similar process for the training of a such a model and dives into the technical details of an architecture that appears similar:
https://arxiv.org/pdf/2311.16121
Hello,
Thank you for asking and gratitude to my colleague for citing related research.
Given the broad interest in this topic we'd appreciate it if you took a moment to send us an enhancement request to publish sample code. You can do this with the Feedback Assistant.