Sensitive content
This media may contain sensitive content.
Loading video...
Video Failed to Load
Researchers presented Vid2Avatar, a method that creates human avatars from in-the-wild videos via self-supervised scene decomposition. See more: #AI #ArtificialIntelligence #3dart #research
247,468 views • 3 years ago •via X (Twitter)
9 Comments

MR3D-Dev3 years ago
So instead of a giant green screen I should just go to a soccer field, thanks for the idea.

Karet3 years ago
When they tell you to act normal

InfinityCg3 years ago
All this shit and still no automatic UVs 😭

BADASS Studios3 years ago
This would be really interesting to see implemented in a metaverse platform. Imagine the digital dance parties!

kivanc3 years ago
Is that real time normal map?

Lazer Eyes3 years ago
he look normal

Squaremusher3 years ago
Did we just skip mocap altogether?

Tioaoa3 years ago
O hell yeh Nonstop!

_man_Art_man_3 years ago
Woooooow!!! That is awesome and crazy !!! Switch it ON for all !! We do not longer need bloody rigs 😅😅😅


