Re:Magic123: One Image to High-Quality 3D Object Generation
by timlod on Friday August 04, 2023 @04:31AM
(#36997127)
Do you have any source for scene reconstruction being hollywood-quality given 50+ images 10 years ago (assuming the images don't come from a controlled environment)?
I can find for example this from 2016: https://substance3d.adobe.com/magazine/go-scan-the-world-pho...
However, there's still a lot of manual work involved, and you don't easily get near-perfect PBR textures (which would be what I'd consider hollywood-quality).
I'd say the devil is in the details - if you want the best quality, you'd still need to control a lot of the environment.
The more assumptions you can bake into the parameters of some model, the more degrees of freedom you get in the actual measurement process (e.g. reducing the amount of actual data necessary).
Re:Magic123: One Image to High-Quality 3D Object Generation
by fxtentacle on Friday August 04, 2023 @03:05PM
(#37004387)
Agisoft PhotoScan was publicly released in 2010 and I know someone who used the beta for scenes in a movie that hit cinemas in 2014.
But yes, the images totally came from a controlled environment. They rented like 50 similar cameras and hardware-synchronized the shutters.
Re:Magic123: One Image to High-Quality 3D Object Generation
by wkat4242 on Friday August 04, 2023 @06:00AM
(#36997750)
True but 50+ images only work if they're good quality.
What would really make a difference if you could make a decent model from 30 images snapped by a drunk teenager on their $200 budget phone in bad lighting.
If money and resources are not an object then yeah it's easy but for most people it is.
Re:Magic123: One Image to High-Quality 3D Object Generation
by fxtentacle on Friday August 04, 2023 @03:06PM
(#37004402)
Renting a matterport pro is like $200 per day, so that should be well within the budget of most hobbyists
From what I understand, they use the text keywords detected from the image as guidance and they also apply a loss between the current diffusion state and the source image. In effect, this is stable diffusion for 3D shapes but with clever conditioning. That means this algorithm will also work just fine if you have 2+ input images.