News for hackers. Stuff that matters.
Re:Super Resolution by light_hue_1 on Thursday March 18, 2021 @07:02PM (#26508464)
This is the actual original meaning of the word "super resolution". The idea is that you use a prior about a specific image, domain, type of image, etc. to enhance the resolution.

Super-resolution was already the name for this field in this 1987 review! https://kmh-lanl.hansonhub.com/publications/imrecov.pdf But 1987 is pretty recent as far as this field is considered. A. W. Lohmann and D. P. Paris talked about super-resolution this way in 1964! https://www.osapublishing.org/ao/abstract.cfm?uri=ao-3-9-103...

So no. It's not annoying that super-resolution is the name of this field. The name predates the entire field of image processing, it predates the invention of the digital camera! And it is the original use of the title "super resolution", people that do this in hardware adopted the name later.

Re:Super Resolution by ska on Thursday March 18, 2021 @07:16PM (#26508579)
I think you misread me (so clearly I articulated poorly); the thing that is annoying is that super resolution in the sense you refer to is categorically a different thing that the common usage of super resolution in (particularly single image) digital processing. The usage existed, as you and I noted, before it came into digital image processioning.

Because of this, conversations around it are often confused, and it would be clearer if there were a different terminology for the latter.

Re:Super Resolution by meowface on Friday March 19, 2021 @03:10AM (#26510733)
What would be a better term for this type, then? "Inferred/approximated super resolution", or something?