News for hackers. Stuff that matters.

A comment on Super Resolution: Image-to-Image Translation Using Deep Learning in ArcGIS Pro.

Re:Super Resolution: Image-to-Image Translation Using Deep L... by RicoElectrico on Friday February 17, 2023 @10:30AM (#34835742)
Bing uses similar treatment on their satellite imagery and OSM mappers (who are permitted to use it) have been complaining it looks more like painting than actual imagery.

Satellite images have 0.4 m resolution or better these days, what matters most is good color quality (e.g. hyperspherical pansharpening), sensor dynamic range and good lighting conditions (sun elevation in particular).

[ Parent | on HN ]
Re:Super Resolution: Image-to-Image Translation Using Deep L... by razor_router on Friday February 17, 2023 @10:40AM (#34835872)
What kind of technology does Bing use to treat their satellite imagery?
[ Parent | on HN ]
Re:Super Resolution: Image-to-Image Translation Using Deep L... by shiftpgdn on Friday February 17, 2023 @10:45AM (#34835956)
30/50cm per pixel are the maximum allowable by law in the US for "civilians". I'm sure we could do even better if allowed.
[ Parent | on HN ]
Re:Super Resolution: Image-to-Image Translation Using Deep L... by astrange on Friday February 17, 2023 @11:22AM (#34836615)
"Satellite" images on maps are often not from satellites but rather planes or drones.

I guess with this technique you could do ML image synthesis guided by SAR satellites - that way you could sort-of look through clouds from space, as long as you don't mind the image being largely fictional.

[ Parent | on HN ]
Re:Super Resolution: Image-to-Image Translation Using Deep L... by m2fkxy on Friday February 17, 2023 @11:09AM (#34836375)
Some companies are working on 10 centimeters.
[ Parent | on HN ]
Re:Super Resolution: Image-to-Image Translation Using Deep L... by TOMDM on Friday February 17, 2023 @01:48PM (#34838687)
I'm having trouble finding citations on the specific law, but this website states that the US has capped satellite imagery for civilian use at 0.31 m

https://pubs.acs.org/doi/10.1021/acs.est.0c02365

[ Parent | on HN ]