Quote:
Originally Posted by matlud
Discussing the role of AI in astro processing can seem a bit like opening pandoras box �� For sharpening and noise reduction afaik there is the Xterminator range (which I understand was trained on Hubble data that was convolved, so it represents a best case scenario as far as detail) and Topaz. One criticism of Topaz is it is mainly trained with terrestrial images but in both cases it’s a bit of a black box to most of us as to exactly what the neural network is doing. Like all tools I think you can go too far with them and create artefacts, but if you use them carefully and compare back and forwards with your raw data to make sure its enhancing what you have captured, I think they are useful.
|
Everything you say there sounds pretty spot on to me. It just feels like every time I see an image these days, that looks detailed, I am second guessing how it was done and whether that detail is real or kinda conjured and even made up
I used to be good at picking the filters used in processing and when they were applied too heavily but this new AI based filtering palava is much more tricky. As you say, it's fairly easy to keep an eye on changes in your own data, as you progress the processing but having to blink others images, just to verify it's reality, is more of a pain...and what to blink it with? Hubble?
Not that I want to, but certainly no chance of checking your image, its a brand spanking new object
Anyway, sorry for nudging the lid of Pandoras box
and again, very well done to you and the team
...and look forward to some Olsen-Ludgate brilliance
Mike