Nobody testing DxO PureRAW seems to care about how much detail the neural network "invents", they just throw a noisy RAW file and look at the result -> WOW!
To find out we need a noiseless version of the scene and compare it with the result output from DxO PureRAW (DeepPRIME) when applied to a noisy version of the same scene.
Scene:
http://guillermoluijk.com/misc/dxoprimeescena.jpg
100% crops test (LEFT: noiseless capture, CENTRE: noisy capture, RIGHT: processed noisy capture):
http://guillermoluijk.com/misc/dxopureraw.jpg
Just comparing the output (right) with the noisy unprocessed capture (centre), the result is awesome, but when we look at the original scene some considerations have to be made:
1. Text masked by noise is cleaned, but its lines and traces are not recovered, as expected.
2. The most interesting spot: the neural network interprets and creates non existent edges and shaded facets, which are feasible looking at the noisy image but didn't exist in the scene
3. The neural network tends to simplify complex structures: the carvings on the leather mask are a series of curves but are interpreted more like linear shapes
4. Fine detail in the scene, completely lost in the noisy shot, is lost and interpreted as a plain colour area (with some fine gaussian-like grain at pixel level)
5. Flat colours are very well recovered, as would be with most noise reduction procedures
In the real world, this kind of software will be used without being able to compare with the real detail, so most photographers will consider valid all the fake detail recreated by the NN.
But watch out! those clean of noise feathers could belong to some other bird, not exactly the one you photographed.
Regards
