正在加载视频...
视频加载失败
Alibaba presents MIMO Controllable Character Video Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their... show more
148,955 次观看 • 1 年前 •via X (Twitter)
10 条评论

AK1 年前
discuss:

A.I.Warper1 年前
Ali “no code, code coming soon, jk it’s never coming” baba

Kamus1 年前
these are great, but i wish everytime i read on one of these, i could try it out immediately.

Aswanth achoo'z1 年前
Rip motion tracking 😯

Curt Anderson1 年前
Isn't this very similar to what ControlNet does? ControlNet also is able to make accurate wireframe interpretations of poses, but this does seem more coherent.

Tomy Kwong 𝕏1 年前
MIMO as in Wi-Fi signalling? /s

txh1 年前
open-source?

Fareesh Vijayarangam1 年前
new fone who dis

Diallo Ciré1 年前
When I say I want to do research in CV this might be the reason

ari1 年前
I'd be cautious as these Alibaba papers will never release the code and also rarely publish working demo or product. Just impressive paper videos
