Hacker News new | ask | show | jobs
by 0x02A 822 days ago
The original paper doesn't work well with few-shot learning. I'm assuming that there is only one camera angle for each pre-rendered background. For single image to 3D, check out DreamGaussian. [1]

[1] https://arxiv.org/pdf/2309.16653.pdf
1 comments
Cloudef 822 days ago
Pre-rendered in this context means you still have access to the full 3d scene so you can generate the full gaussian splatting model from that. The benefit here would be to lower the cost of rendering that complicated scene. There is a game called Fantasian (by the former FF dev) that uses real-life dioramas as backgrounds, I bet this tech would've been perfect fit for that too.
link
0x02A 822 days ago
Oh I see. That's a pretty cool use case. Not sure how GS would perform on non-photorealistic scenarios, but certainly worth a try.
link