Live data from Hacker News

Viewing profile — citnaj

citnaj

HN member
Joined
Fri, Nov 02, 2018, 7:17 PM UTC
HN karma
126
Public activity
23 items

About citnaj

No profile information was provided.

Recent public activity

  1. comment
    Comment #19824719

    Hello- Jason here (one of the authors). I'll answer questions! I might not get to them right away as I'm about to go to bed.

  2. story
  3. comment
    Comment #18983798

    OMG dude that's such an accurate description of my life at that time.

  4. comment
    Comment #18982632

    Very cool project. And 11th grade!?! Wow....I definitely wasn't doing anything like this at that age. Something that came to mind as a potential way to get clearer and more realist…

  5. comment
    Comment #18555648

    That is exciting! I'll be watching on Twitter :)

  6. comment
    Comment #18555130

    >"More recently, there is a shift towards using a Transformer architecture, and right now I’m experimenting with that as well." I'm really curious- any early results to share on th…

  7. story
  8. comment
    Comment #18441626

    Update: I got this working, and dude- it's so awesome in every way. This is the most substantial improvement I've seen yet. Most importantly- it massively reduces memory requiremen…

  9. comment
    Comment #18383877

    Yeah the more I churn over this idea in my head the more excited I get about it. This really sounds like a big win. I'm not sure what I want to do about the Kanban board versus iss…

  10. comment
    Comment #18378298

    Oh shit yeah that really does look good! Amazing really. Ok...I'm going to put these notes on the project board. Yes..I definitely glossed over the proposed workaround and I apolog…

  11. comment
    Comment #18368782

    That's very interesting to point out Thank you!

  12. comment
    Comment #18368765

    I was actually thinking along the same lines because yeah...if you could break this problem down into smaller pieces, it would probably be the most effective way to reduce memory r…

  13. comment
    Comment #18368739

    I should add too, just to be clear- I'm not at all involved in academia.

  14. comment
    Comment #18368732

    I understand the frustration and in fact share it to a certain extent with science in general. Keep in mind that this wasn't intended to be published as a paper or anything like th…

  15. comment
    Comment #18366496

    Author here. That's actually what I find quite fascinating myself about the results- that they look almost perfect at first glance, yet you drill down a bit closer and you see anot…

  16. comment
    Comment #18366468

    LOL I think that'll be my go to excuse for lack of documentation for now on....

  17. comment
    Comment #18366458

    Added this to the Known Issues section.

  18. comment
    Comment #18366421

    Yeah I tried pointing that out in the Known Issues section by alluding to adjusting the size parameter as a means to get the best images. But I think I'll just go ahead and be crys…

  19. comment
    Comment #18366016

    Author here. Easy to answer that one- altering the training photos with random lighting/contrast changes (yet keeping the color targets the same) really helped to deal with varying…

  20. comment
    Comment #18365989

    Author here: It's early, and currently resolution is limited primarily by model size. Which drives me nuts. It's one of my top priorities to address because that would be a great i…

  21. comment
    Comment #18365952

    Author here. Yeah you're basically right. GANs vastly improve the situation though because being safe with "green for grass, blue for sky, brown as default" doesn't work in the Gen…

  22. comment
    Comment #18365919

    Author here. Yes, it drives me nuts :)

  23. comment
    Comment #18365911

    Author here- So I'll just be brutally honest on that one- not all renders are doing that. I cherry picked the one that did that because yeah, it's amazing. There's a simple explana…