Muhammed Kocabas

It is still giving this OpenGL error: ``` Traceback (most recent call last): File "demo.py", line 347, in main(args) File "demo.py", line 250, in main renderer = Renderer(resolution=(orig_width, orig_height), orig_img=True,...

@x0rzkov I am still getting errors with the current one, I will commit and merge this PR once I complete it. Thanks for your efforts!

Hi @kallivad this PR is a work in progress. It is not finished and tested. Please use `pip` or `conda` to install the requirements.

Hi @Pranjal2041, This looks awesome. I plan to test it over the weekend, if everything works fine I will merge it. Thanks for your time and effort!

Hi @mayoudong1993, We didn't test our code on Windows, so it is a bit difficult to figure out the problem. And it seems the problem is related to pyrender installation,...

Thanks @StephenGreat for the solution. Is this the only modification you did to make VIBE work on Windows?

Hi @alexrichardson21, Yes, it is definitely possible. We rely on SPIN pretrained backbone. So, you would need to train SPIN with proper data augmentation. I plan to release an occlusion...

You can give https://github.com/mkocabas/PARE a try.

Hi @hongsukchoi, Thanks for your suggestion! Your point about availability of Human3.6M and NBA is correct. Therefore, we could not use NBA for training. We needed to use Human3.6M mosh...

Hi @sisse008, You need to follow the data preparation instructions (https://github.com/mkocabas/VIBE#training) to get the preprocessed dataset files for training.