Author Topic: ML dual iso in academic study  (Read 1758 times)

70MM13

  • Hero Member
  • *****
  • Posts: 551
ML dual iso in academic study
« on: May 28, 2022, 01:15:28 PM »
Has everyone seen this paper from 2016?
I'm really curious about thoughts regarding this, particularly the performance of the ML method, from the upper echelons...
Dual iso has so much promise.  It requires a new approach to achieve any of its potential.

https://repositori.upf.edu/bitstream/handle/10230/28210/Bertalmio_ElectronicImaging2016_high.pdf?sequence=1&isAllowed=y

70MM13

  • Hero Member
  • *****
  • Posts: 551
Re: ML dual iso in academic study
« Reply #1 on: May 30, 2022, 08:43:28 PM »
does no one have any thoughts about his approach?

names_are_hard

  • Developer
  • Hero Member
  • *****
  • Posts: 506
  • 200D idiot
Re: ML dual iso in academic study
« Reply #2 on: May 30, 2022, 09:12:26 PM »
They describe the algorithm, I didn't spend much time on it but it looks like there's enough info to implement it.  If someone was willing to spend the time to do that, it would be possible to compare the methods.

What kind of discussion were you hoping for?

70MM13

  • Hero Member
  • *****
  • Posts: 551
Re: ML dual iso in academic study
« Reply #3 on: May 30, 2022, 11:35:05 PM »
I'm curious if anyone who is familiar with the current approach would have any thoughts or inspiration resulting from reading it.

names_are_hard

  • Developer
  • Hero Member
  • *****
  • Posts: 506
  • 200D idiot
Re: ML dual iso in academic study
« Reply #4 on: May 31, 2022, 01:10:11 AM »
Okay.  Mine is basically: sounds like it would be interesting to test it.