I'm curious about the technical details behind the RAW denoising in Adobe Lightroom, DxO DeepPRIME, etc. What makes these propreitary solutions so much better than open-source models like RawNIND?
Here's the RawNIND paper
https://arxiv.org/pdf/2501.08924
I'd be inclined to say that DxO could have done something similar but just spent more resources developing it.