Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Example data to run jupyter notebook #1

Open
YuxuanSnow opened this issue Apr 7, 2024 · 1 comment
Open

Example data to run jupyter notebook #1

YuxuanSnow opened this issue Apr 7, 2024 · 1 comment

Comments

@YuxuanSnow
Copy link

Hi Sanket,

thanks for providing this training script! I wonder if you can provide a set of RGB and CCM images to let me run the jupyter notebook? I would like to quickly explore this and provide some feedbacks. I had some of experiments of purely overfit flexicubes to a MLP-based SDF, which struggles to work already; Thus i would like to further investigate to your training repo;

It would be great if you can provide the code to render RGB and CCM from a textured obj file!

Best,
Yuxuan

@SanketDhuri
Copy link
Owner

SanketDhuri commented Apr 8, 2024

I have provided of RGB and CCM images as you asked.

Regarding the code to generate RGB and CCM images from a textured OBJ file, I don’t have a specific script for that. For the RGB images, I manually took all the necessary views using the Windows 3D viewer. As for the CCM images, I changed the first stage of inference, inserted images from a local directory in PIL format, and implemented code to save all the images produced by the second stage.

The input for stage two was ‘5.jpg’ along with an array of PIL images, which included JPEGs numbered from 0 to 5.

I will make automated code for it if possible..

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants