[HN Gopher] HumanRF: High-Fidelity Neural Radiance Fields for Hu...
___________________________________________________________________
HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
Author : Keats
Score : 49 points
Date : 2023-05-15 12:06 UTC (10 hours ago)
(HTM) web link (synthesiaresearch.github.io)
(TXT) w3m dump (synthesiaresearch.github.io)
| mdrzn wrote:
| Can't wait for a The Sims version where you can "upload yourself"
| just with a selfie. Gaming will become very personalized.
| aperrien wrote:
| Sounds kind of like Nintendo Mii's, Which were on the 3DS and
| WiiU in 2012.
| posterboy wrote:
| Lol, adding a mugshot was enabled in EA's NHL 2000'ish. Didn't
| look good to be honest and hasn't made a difference.
| rpaddock wrote:
| The 1981 cult classic movie Looker becomes real.
|
| Do we have the understanding of neuro anatomy today to make a
| Light Ocular-Oriented Kinetic Emotive Responses (L.O.O.K.E.R.)
| device? We certainly have the technology.
|
| https://www.imdb.com/title/tt0082677/?ref_=kw_li_i
| magixx wrote:
| Given their setup of 120 to 160 cameras to capture the
| performances, the results seem kinda just "meh". While it's neat
| that they were able to generate 3D models from all that data,
| it's also not very surprising. Maybe their data processing
| methods are more impressive than their end results. It reminds me
| of the bullet time rigs used for The Matrix over 20 years ago
| except I don't think they were creating 3D models of people.
| gorkish wrote:
| I don't quite think you fully understand the nature of NeRF
| reconstruction. I believe being dismissive of this technology
| is extremely shortsighted.
| somethingsome wrote:
| Their results are clearly 'meh' given the number of inputs, in
| [0] they use only 2-4 cameras in real-time to achieve the same
| or better quality (see their supplementary material). In [1] is
| a video view synthesis generated by 4 cameras.
|
| [0] https://ieeexplore.ieee.org/document/9590541
|
| [1] https://youtu.be/ONO_bc6vpf0
| VikingCoder wrote:
| ...yeah, but there was no interpolation happening in the
| original The Matrix. Every single frame we saw corresponded to
| a single camera that took a photo.
|
| New works like this one allow interpolation.
|
| It's fair to ask if this is similar to what we saw in the
| Matrix sequels, where I believe they used different solutions.
| But again, I think the Matrix sequels mostly used entirely CG
| actors...? Not interpolation of recorded acting.
| kranke155 wrote:
| They are generating NERFs out of people in motion and that is
| novel.
|
| I work in film VFX (related) and the tech that was used for the
| matrix was nowhere near this.
|
| I dare say you might be underinformed about this topic.
| SantalBlush wrote:
| What is your opinion on the future of film and acting given
| the trajectory of AI and tech like this? Do you see
| significant changes to the way movies will be shot, or to the
| level of involvement of human actors in film?
| kranke155 wrote:
| I'm a lowly worker but.
|
| Not really ? Film acting is a delicate art. And it's 1000x
| faster than computer animation. You can film a cheap film
| in 3 weeks maybe, on a tight schedule. The actors will be
| able to deliver what you need.
|
| Animating the equivalent film would cost you something
| between 1-3 years.
|
| So no I don't see a way that any of this will affect film
| actors. We already have fully functional digi doubles, they
| just don't use NERFs.
|
| Pointing a camera at something / someone interesting is
| still somewhere around 1000x more efficient than computer
| animation. I don't see a near or mid future where this
| changes.
| Valgrim wrote:
| I think the appeal in this NeRF tech in in the ability to
| use both real capture information, like traditional
| filmmaking, AND the ability to reframe, refocus,
| recompose images, like in 3d scenes.
| mustacheemperor wrote:
| The closest technology I had previously seen to this was MS'
| volumetric video capture for "holoportation" and 3D video
| recording at their SF Reactor facility and this seems like a
| significant improvement[0]. That also used an array of cameras
| in a studio setting but the resulting color and model quality
| wasn't close to as accurate and sharp as these examples.
|
| Are there other examples of similar tech in use at a comparable
| level of quality in recent history? Against any comparable end
| results I've personally seen, it looks very impressive.
|
| [0] https://www.microsoft.com/en-us/mixed-reality/capture-
| studio...
| notjustme wrote:
| This is actually really impressive. Extrapolate this 12 months...
___________________________________________________________________
(page generated 2023-05-15 23:01 UTC)