Results 1 to 11 of 11

Thread: Nvidia GANverse3D "inflates flat images into realistic 3D models"

  1. #1
    HEXUS.admin
    Join Date
    Apr 2005
    Posts
    31,709
    Thanks
    0
    Thanked
    2,073 times in 719 posts

    Nvidia GANverse3D "inflates flat images into realistic 3D models"

    In a (video) demo, Nvidia shows off a playable recreation of the famous Knight Rider KITT car.
    Read more.

  2. #2
    Registered User
    Join Date
    Mar 2019
    Posts
    13
    Thanks
    0
    Thanked
    0 times in 0 posts

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Riiiiiiiiiiiiight

  3. #3
    Long member
    Join Date
    Apr 2008
    Posts
    2,427
    Thanks
    70
    Thanked
    404 times in 291 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    The 3D KITT looks like they've turned the brightness so far down there's no detail to miss.

    In short; thanks Nvidia, I hate it.

  4. #4
    Senior Member
    Join Date
    Aug 2019
    Posts
    902
    Thanks
    12
    Thanked
    34 times in 26 posts
    • Gentle Viking's system
      • Motherboard:
      • Gigabyte Aorus extreme X399
      • CPU:
      • TR 1920 X
      • Memory:
      • G Skill 64GB ( 8 X 8 ) PC3600 @ 3400
      • Storage:
      • Samsung evo 500GB nvme - 256GB Kingston SSD - 4TB spinning disk
      • Graphics card(s):
      • Powercolor 5700 XT red devil
      • PSU:
      • Corsair RM850I
      • Case:
      • Working on it, done summer 2020
      • Operating System:
      • windows 10 Ulti
      • Monitor(s):
      • 27" iiyama GB2788HS
      • Internet:
      • docis 3.1 cable 1000/100 mbit

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    well as a guy that can not draw perspective / 3D it might be interesting.
    But yeah look like ray tracing,,,,,, it will probably be better in the 2.0 version next year.

  5. #5
    Long member
    Join Date
    Apr 2008
    Posts
    2,427
    Thanks
    70
    Thanked
    404 times in 291 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Quote Originally Posted by Gentle Viking View Post
    well as a guy that can not draw perspective / 3D it might be interesting.
    But yeah look like ray tracing,,,,,, it will probably be better in the 2.0 version next year.
    Indeed, it's something that'll be better with more machine learning and refinement. Interesting and could be great for indie games makers.

    If you can't tell, the origional comment was written when my meds had worn off and now I'm all drugged up again and happy.

  6. #6
    Senior Member
    Join Date
    Mar 2019
    Location
    Northants
    Posts
    309
    Thanks
    4
    Thanked
    22 times in 19 posts
    • KultiVator's system
      • Motherboard:
      • Aorus x570 Ultra
      • CPU:
      • Ryzen 3900x
      • Memory:
      • G.Skill 32GB (2x16gb) 3600Mhz
      • Storage:
      • 5TB of NVMe storage (most of it on PCIe4) + Various SATA SSDs & HDDs
      • Graphics card(s):
      • Aorus RTX 2080 Super OC 8GB
      • PSU:
      • Corsair RM750x
      • Case:
      • Phanteks Eclipse P600s (Black & White Edition)
      • Operating System:
      • Windows 10 Pro
      • Monitor(s):
      • AOC 32" 4K IPS / ASUS 24" ProArt 1200p IPS / GStory 1080p/166Hz GSync/FreeSync IPS / Quest 2 HMD

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Very suspect... you show it the front of a car and it 'knows' what the (out of sight) rear light cluster looks like?

    This sets false and really dubious expectations.
    Last edited by KultiVator; 20-04-2021 at 09:53 AM.

  7. #7
    Long member
    Join Date
    Apr 2008
    Posts
    2,427
    Thanks
    70
    Thanked
    404 times in 291 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Quote Originally Posted by KultiVator View Post
    Very suspect... you show it the front of a car and it 'knows' what the (out of sight) rear light cluster looks like?

    This sets false really dubious and expectations.
    To be fair, if you're making a model for a game and it doesn't have to be a proper replica, machine learning could do this to an acceptable standard. You're not going to get the back correct, but a large enough dataset could certainly get results suited to the "make 3D model from 2D photo in a single press" market.

  8. #8
    Senior Member
    Join Date
    Mar 2019
    Location
    Northants
    Posts
    309
    Thanks
    4
    Thanked
    22 times in 19 posts
    • KultiVator's system
      • Motherboard:
      • Aorus x570 Ultra
      • CPU:
      • Ryzen 3900x
      • Memory:
      • G.Skill 32GB (2x16gb) 3600Mhz
      • Storage:
      • 5TB of NVMe storage (most of it on PCIe4) + Various SATA SSDs & HDDs
      • Graphics card(s):
      • Aorus RTX 2080 Super OC 8GB
      • PSU:
      • Corsair RM750x
      • Case:
      • Phanteks Eclipse P600s (Black & White Edition)
      • Operating System:
      • Windows 10 Pro
      • Monitor(s):
      • AOC 32" 4K IPS / ASUS 24" ProArt 1200p IPS / GStory 1080p/166Hz GSync/FreeSync IPS / Quest 2 HMD

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Quote Originally Posted by philehidiot View Post
    To be fair, if you're making a model for a game and it doesn't have to be a proper replica, machine learning could do this to an acceptable standard. You're not going to get the back correct, but a large enough dataset could certainly get results suited to the "make 3D model from 2D photo in a single press" market.
    Yeah - I wasn't clear in my comment... the video was pretty sparse and made the whole thing seem 'automagic' rather than emphasising the reality of the training needed to get the AI to be able to even recognise a particular object in a photo.

    There's definitely uses for this kind of technology - just the real capabilities of it need a lot of ground work to prepare them for a specific task.

  9. #9
    Long member
    Join Date
    Apr 2008
    Posts
    2,427
    Thanks
    70
    Thanked
    404 times in 291 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Quote Originally Posted by KultiVator View Post
    Yeah - I wasn't clear in my comment... the video was pretty sparse and made the whole thing seem 'automagic' rather than emphasising the reality of the training needed to get the AI to be able to even recognise a particular object in a photo.

    There's definitely uses for this kind of technology - just the real capabilities of it need a lot of ground work to prepare them for a specific task.
    Part of me wonders if they'll just give it a massive internet trawling dataset to make it automagic?

  10. #10
    Member
    Join Date
    Apr 2019
    Posts
    104
    Thanks
    1
    Thanked
    1 time in 1 post

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Didn't look useable. If they could give it 50 images of kitt they had just scraped off the web that came with different lighting/backgrounds/etc and it was able to use them all to produce a near perfect 3d image then I'd be more impressed.

    Even then it would just be a static 3d model, so even better if they could show it the images and then get the AI to watch the backlog of knight rider episodes and it comes up with a perfect 3d kitt with full animation.

  11. #11
    Long member
    Join Date
    Apr 2008
    Posts
    2,427
    Thanks
    70
    Thanked
    404 times in 291 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: Nvidia GANverse3D "inflates flat images into realistic 3D models"

    Quote Originally Posted by Dribble View Post
    Didn't look useable. If they could give it 50 images of kitt they had just scraped off the web that came with different lighting/backgrounds/etc and it was able to use them all to produce a near perfect 3d image then I'd be more impressed.

    Even then it would just be a static 3d model, so even better if they could show it the images and then get the AI to watch the backlog of knight rider episodes and it comes up with a perfect 3d kitt with full animation.
    I suspect it's the sort of thing that'll find most use as placeholders for game / graphics development. Something you can use to put a proper 3D model in whilst someone is busy making the actual model without any major time / effort input. But, I also have no idea how games are designed, so that may be total bull.

  12. Received thanks from:

    Strawb77 (24-04-2021)

Thread Information

Users Browsing this Thread

There are currently 1 users browsing this thread. (0 members and 1 guests)

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •