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

Can I read numpy data from the depth,normal and silhouette image? #58

Closed
CaolLiu opened this issue Mar 11, 2020 · 4 comments
Closed

Can I read numpy data from the depth,normal and silhouette image? #58

CaolLiu opened this issue Mar 11, 2020 · 4 comments

Comments

@CaolLiu
Copy link

CaolLiu commented Mar 11, 2020

Hi,
I know that the depth,normal and silhouette image can be visualized from their numpy data, But can I read numpy data from the depth,normal and silhouette image?

@xiumingzhang
Copy link
Owner

Hi, sorry for the delayed response.

Are you referring to the raw, floating-point values? If so, you'd have to render the raw values with Mitsuba using our released XML files yourself.

Please feel free to reopen if you have further questions.

@CaolLiu
Copy link
Author

CaolLiu commented Mar 14, 2020

Thank you for your reply.
Are the raw, floating-point values obtained from .obj files by using the XML files ? And if I want to obtain the raw muti-views obj_spherical and the depth_spherical data from one three-dimensional model(as the each object captured in 20 random views), should I also use the XML files ?

@xiumingzhang
Copy link
Owner

By "using Mitsuba and the XML files," I meant rendering the depth, normal, and silhouette images into EXR files, and then reading the floating-point values from there.

You can of course do ray casting to the 3D model to get all these values (equivalent to doing the rendering yourself instead of with Mitsuba), but I think it'd be easier to just use Mitsuba.

@CaolLiu
Copy link
Author

CaolLiu commented Mar 14, 2020

ok, thank you ^_^!

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