Live data from Hacker News

Viewing profile — TobiasEnholmX

TobiasEnholmX

HN member
Joined
Thu, Feb 23, 2023, 10:17 AM UTC
HN karma
52
Public activity
15 items

About TobiasEnholmX

tobias@backdrop.tech Founder

Recent public activity

  1. comment
    Comment #43125974

    Yeah, exactly. Gaussian Splatting works great when you have an image (or set of images) and want to reconstruct a whole scene in 3D, but it treats everything as a unified point-bas…

  2. comment
    Comment #43103833

    Appreciate the feedback! Sounds like you're looking for more of a deep dive into the tech and how it works. This post was more about showing results, but we’ll cover the process an…

  3. comment
    Comment #43102768

    Glad you like it! In the blog post you can find my email, or join the discord https://discord.gg/backdrop

  4. comment
    Comment #43102756

    We’re actually finding that leveraging 3D reduces complexity rather than increasing it. Setting up a 3D scene is getting easier with tools like image-to-3D, and once it's set up, y…

  5. comment
    Comment #43102683

    Fair point! We debated whether to post this here since it's more about examples rather than the full how-to and technical breakdown. Next post, we’ll aim to go deeper into the proc…

  6. comment
    Comment #43102519

    First off, I’d love to hear more about your experience. If you’re up for a chat, shoot me an email at tobias@backdrop.tech, or let me know where I can learn more about what you’ve …

  7. comment
    Comment #43102363

    Yeah, I see what you mean! When we say 3D here, we mean working with actual 3D scenes—models, depth, and lighting—rather than the '3D movie' style like Pixar. The goal is to use 3D…

  8. comment
    Comment #43102348

    I just checked and it works for me, but I'm on IOS. There is a fallback that sends each subscriber to my email as well

  9. comment
    Comment #43102313

    That makes sense! Giving AI a structured starting point so it doesn’t go off the rails is similar to what we're doing with 3D. Instead of letting it hallucinate frame by frame, we …

  10. comment
    Comment #43102306

    Yeah, modeling and animating used to be a huge bottleneck, but with tools like image-to-3D and improving AI animation models, it's getting easier and faster. The goal here isn’t to…

  11. comment
    Comment #43102114

    Good question! When we say '3D' here, we mean using 3D models and scenes as a base to guide AI video generation. The AI isn’t just making things up from scratch—it follows the stru…

  12. comment
    Comment #43102111

    Yeah, that’s pretty much the idea. AI has a lot of freedom when generating each frame independently, which often leads to inconsistencies. By using a 3D base, we’re constraining th…

  13. comment
    Comment #43101775

    AI-generated video struggles with consistency. Flickering, weird proportions, and characters changing. I tried using 3D as a way to get more consistency. Overall, it worked. No sud…

  14. story
  15. comment
    Comment #34908810

    Ambient co-founder here. You're right, thanks for the feedback, we'll update the website with one soon.