I don't really understand why NeRFs would be particularly useful in more than a few niche cases, perhaps because I don't fully understand what they really are. My impression is that you take a bunch of photos in various places and directions, then you use those as samples of a 3D function that describes the full scene, and optimize a neural network to minimize the difference between the true light field and what's de…
Nvidia Research Turns 2D Photos into 3D Scenes
211–220 of 239 posts
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#212It would be really great to recreate loved ones after they have past in some sort of digital space. As I’ve gotten older, and my parents get older as well, I’ve been thinking more about what my life will be like in old age (and beyond too). I’ve also been thinking what I would want “heaven” to be. Eternal life doesn’t appeal to me much. Imagine living a quadrillion years. Even as a god, that would be miserable. That…
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#213Earlier quoted context omitted.
That's more interesting than I realized. In this example, I assumed that the model was generating some sort of 3D mesh representing the woman. Is that not at all the case? Would this technique be unable to generate a model or volumetric information despite being able to reasonably render her from many directions?
No, there is no mesh. A NeRF is a neural network trained to work as a function f(x, y, z, θ, φ). You put in your viewing position (x, y, z) in 3D space and the direction (θ, φ) you're looking into (where θ and φ are the angles for up/down and left/right, respectively), and the function will output a tuple (r, g, b, σ) of the colour (r, g, b) and the material density (σ) of whatever you see at the pixel in that direct…
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#214It would be really great to recreate loved ones after they have past in some sort of digital space. As I’ve gotten older, and my parents get older as well, I’ve been thinking more about what my life will be like in old age (and beyond too). I’ve also been thinking what I would want “heaven” to be. Eternal life doesn’t appeal to me much. Imagine living a quadrillion years. Even as a god, that would be miserable. That…
[1] https://www.sfchronicle.com/projects/2021/jessica-simulation...
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#215Earlier quoted context omitted.
There's so many things we invent with good intentions but in the end go terribly wrong and I think this is one of those things. I think it's ok to mourn and remember the past, but moving on and accepting reality is important to a healthy life. Let's be real though, the startup that makes this but appeals to our worst instincts make bank. I can't imagine how much more messed up future generations will be as we keep ma…
"mourn and move on" is a somewhat Western concept of dealing with death. Plenty of cultures around the world have developed different practices, up to religious forms of ancestor worship.
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#216Is the example the result of just 4 photos? Or more? Are there any other data available, spatial data attached to photos for example? Why they don't explain the scope of achievement properly? edit: I don't think it is just 4 https://news.ycombinator.com/item?id=30810885
The model requires just seconds to train on a few dozen still photos — plus data on the camera angles they were taken from — and can then render the resulting 3D scene within tens of milliseconds
Pretty impressive, but lesser compared to generating it from 4 photos (which imho the movie suggests). Which would be "real magic level of impressiveness" for meRe: Nvidia Research Turns 2D Photos into 3D Scenes
#217Earlier quoted context omitted.
Don't knock it til you try it? I mean, already in recent years people have made some very low fidelity 'resurrections' and gotten some measure of comfort from it, never mind the many years of history of people who visit gravestones to 'chat' (some even believing they get replies to some extent or another). When markov chains were hip, "talk with Charles Dickens!" (play with a markov model trained on his works) was at…
I suppose... but I'll always know that it's some sort of cheap trick to make me think they're still here when really their consciousness ceased. Will the simulacrum age? Will it change? Will it ever surprise me or intrigue me? And if it does, is it something the dead person truly would have done? It's sort of like a photograph; a photograph seems to capture reality but all it shows is some abstraction of a physical r…
Maybe that's fine for some people. To me there's a line where it crosses over into offense. In no way do I think the status quo of my mental well-being is so important that I'd replace someone with a digital robot facsimile.
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#218I don't really understand why NeRFs would be particularly useful in more than a few niche cases, perhaps because I don't fully understand what they really are. My impression is that you take a bunch of photos in various places and directions, then you use those as samples of a 3D function that describes the full scene, and optimize a neural network to minimize the difference between the true light field and what's de…
The pros in the vfx industry still all use reconstructed geometry. And yes, animating or cropping a Nerf is painful. In my opinion, Nerf is more about showing progress in making AI memorize 3D scenes and the hope is that this will lead to actual understanding sometime in the future.
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#219Earlier quoted context omitted.
>Imagine living a quadrillion years. Even as a god, that would be miserable. This seems very subjective, I don't agree at all.
In Ursula Le Guin's book "Changing Planes", there's a story called "The Island of the Immortals." Spoiler alert: living forever is no fun.
Re: Nvidia Research Turns 2D Photos into 3D Scenes
#220I don't really understand why NeRFs would be particularly useful in more than a few niche cases, perhaps because I don't fully understand what they really are. My impression is that you take a bunch of photos in various places and directions, then you use those as samples of a 3D function that describes the full scene, and optimize a neural network to minimize the difference between the true light field and what's de…
If you tried to repro these results (including time & space constraints) using traditional photogrammetry, you would be sorely disappointed. Photogrammetry is great if you have a very solid object that is not shiny or translucent at all. You get a lot of surface color micro-detail and a bit of bumpy meso-detail. But, if something is fuzzy, hairy, or lacey or smokey you are straight-up out of luck. Don't even try. If…