MIMO

MIMO copied to clipboard

Pose 图 F_t 到底是怎么渲染的？How do you render the pose image?

8

what's the actual pose image F_t you render? Is the first colored image type or the skeleton-like type? 最终渲染出来的pose图是pipeline里这个彩色的，还是后文图里那个骨骼？This really makes me confused!  

TZYSJTU

how to install

salmankhalil

Which pretrained human repose model was used?

5

In the "Canonical identity" section, you mention using "a pretrained human repose model" to transform the posed human image to the canonical A-pose result. However, I couldn't find which specific...

luopeixiang

Looks cool, but empty

2

Without the code or weights, it's like giving us an empty gift box—there's nothing inside. It’s basically just a powerpoint.

Sylahri

Code & data release

5

Any plan for releasing data and code?

hungnguyen2611

https://github.com/YuliangXiu/PuzzleAvatar/ 4hrs to create avatar + commercially prohibitive license ... but good codebase - also worth checking out -https://github.com/NVIDIAGameWorks/kaolin/

johndpope

Dear MIMO Team, I've discovered a website that I think is falsely using the MIMO name to offer subscription services and charge users without delivering the promised AI services. Here's...

jjhaggar

"Expressive Whole-Body 3D Gaussian Avatar" + with code - https://github.com/mks0601/ExAvatar_RELEASE

2

props to @mks0601 https://github.com/mks0601/ExAvatar_RELEASE https://github.com/mks0601/ExAvatar_RELEASE/raw/main/assets/teaser_compressed.gif

johndpope

Will you release code and models?

1

A gradio app that takes image and driving video as input and generates scene would be amazing Also it works with image input or it requires 3d mesh or such?

FurkanGozukara

Thank you for your excellent work.  How to connect latent codes Z = {z1, z2, . . . , znv} with SMPL (i.e. 3D pose)? Why do all frames...

Delicious-Bitter-Melon