Re:Photorealistic Monocular 3D Reconstruction of Humans Wear...
by jayd16 on Tuesday April 26, 2022 @03:24AM
(#31164904)
Is it just me or does it look like the AI is just pasting a blurry version of the front to fill in the back? You can see hints of necklines on backs, or the red from a dress showing where a black overcoat should be.
[ Parent
| on HN ]
Re:Photorealistic Monocular 3D Reconstruction of Humans Wear...
by scoopertrooper on Tuesday April 26, 2022 @05:47AM
(#31165576)
It knows the neck area can’t be the same between front and back, but it doesn’t know if it should sample the skin or cloth textures to fill the gap, so it just takes a blend of both.
I guess, by hedging this way, it managed to improve its evaluation score without having to learn how clothes actually work.
Re:Photorealistic Monocular 3D Reconstruction of Humans Wear...
by SimplyUnknown on Tuesday April 26, 2022 @05:59AM
(#31165626)
It's definitely not perfect, but I'd argue that it is better than a "blurry front paste". For example, it doesn't place breasts on the back. Also, for the polo shirt example the model is doing significantly better than copying the v-line of the front of the shirt and shows a round collar. I think it is pretty impressive and one could argue the model has somewhat learned what a human looks like from the back given the clothing of the front, even though it is quite blurry.
Re:Photorealistic Monocular 3D Reconstruction of Humans Wear...
by esquivalience on Tuesday April 26, 2022 @03:37AM
(#31164966)
Great observation