Today I was playing with a new 2D-image-to-3D AI models called "DreamGaussian". I gave it a picture of me and asked the AI to translate it to 3D.
Fun to play with, but the quality and detail of the output is still low. I'm sure it'll get better soon.
The model first generates a low-detail 3D model in about 120s (top), then a higher-detail in about 60s (below).
At the end of the video, I switched to Adobe Dimension to view 3D model in higher detail.
I also tried the model with mini isometric versions of the Golden Gate bridge and UC Berkeley's Sather tower, but the output was garbage.
I think this works better with discrete objects and humanoid / animal like shapes.
Gabor Cselle