Live data from Hacker News

Viewing profile — nobbis

nobbis

HN member
Joined
Fri, May 18, 2012, 2:54 PM UTC
HN karma
289
Public activity
96 items

About nobbis

No profile information was provided.

Recent public activity

  1. comment
    Comment #44334025

    ROS 1 had schema evolution (rosbag migration) 15 years ago

  2. comment
    Comment #44250931

    Understood. Thanks for the clarification.

  3. comment
    Comment #44250851

    Wait, you renamed Forge ( https://forge.dev ) released last week by World Labs, a startup that raised $230M. Is this "I worked with some friends and I hope you find useful" or is i…

  4. comment
    Comment #37421731

    > The big difference of course, based on reading this, is that NeRF models the whole light transmission function ("radiance field") whereas this seems to model only the boundary co…

  5. comment
    Comment #35361474

    IANAL but I assume so. "Employee of a competing company" (whatever that means) isn't a protected class.

  6. comment
    Comment #35361123

    And Matterport will never see them coming, as their employees are banned from using Luma: Competitors: No employee, independent contractor, agent, or affiliate of any competing 3-D…

  7. comment
  8. comment
    Comment #34263178

    Rising rates don't make the dollar stronger. There's no empirical relationship between interest rates and exchange rates.

  9. comment
  10. comment
    Comment #33111514

    Yes, although not complete noise – probably empty. Haven't checked but assume there's regularization of the NeRF parameters.

  11. comment
    Comment #33111048

    DreamFusion doesn't directly build a 3D model from those generated images. It starts with a completely random 3D voxel model, renders it from 6 different angles, then asks Stable D…

  12. comment
    Comment #33110459

    Key step in generating 3D – ask Stable Diffusion to score views from different angles: for d in ['front', 'side', 'back', 'side', 'overhead', 'bottom']: text = f"{ref_text}, {d} vi…

  13. comment
    Comment #33109813

    Took a week, as predicted: https://twitter.com/DvashElad/status/1575614411834011651

  14. comment
  15. comment
    Comment #32085030

    We rely on Wasm for Metascan ( https://metascan.ai/explore ) which allows us to use the same rendering code on iOS, the desktop, and the web. Accessing multithreading is limited as…

  16. comment
    Comment #31587580

    Explains the huge remodel of her property here in South Lake.

  17. comment
    Comment #31161952

    iPhone/iPad's LiDAR Scanner.

  18. comment
    Comment #30695102

    6D.ai wasn’t released until 2018. You may be thinking of Abound, which you wanted to license in March 2017. I don’t know of anyone else that had real-time meshing in 2017.

  19. comment
    Comment #30684619

    Interesting - I’ve never observed it kicking in. Would love to know in which circumstances it’s used. I assume you work for Apple to know this so understand if you can’t share more…

  20. comment
    Comment #30684504

    Correlation != causation. Try out our app, Metascan, to see an example of using TSDF with a multi-resolution GPU hashtable that only stores voxel data near surfaces. Or just skim t…

  21. comment
    Comment #30679903

    ORB-SLAM2 is SLAM only (similar to ARKit w/o VIO) so only reconstructs feature points - no surfaces. This research is about surface reconstruction.

  22. comment
    Comment #30679770

    ARKit doesn’t use LiDAR for camera pose tracking. TSDF memory isn’t an issue since Niessner et al. (2013).

  23. comment
    Comment #30679196

    Their research doesn't just integrate depth maps into a TSDF - it uses NN's to incorporate surface priors. I don't recall you having similar real-time meshing functionality in 2016…

  24. comment
    Comment #29787822

    I said "wanted it" not "wanted to build/finance it." Doubt he's given up wanting it. A human can always do better: take Google's results, then remove SEO spam/duplicates, extract m…

  25. comment
    Comment #29787288

    Building costs more than money.