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

if you have tested the changes in the use of VRAM for graphics card rendering before and after compression? #13

Open
smart4654154 opened this issue Aug 11, 2024 · 3 comments

Comments

@smart4654154
Copy link

Thank you very much for your work
The data compression work is excellent
May I ask if you have tested the changes in the use of VRAM for graphics card rendering before and after compression?

@YihangChen-ee
Copy link
Owner

YihangChen-ee commented Aug 12, 2024

Hi, the rendering memory would not change before or after compression. HAC is a pre-decoding technique, which is used to decode the model weights (ie, the Scaffold-GS model) given the input bitstreams. Once the weights are obtained after decoding using HAC, the rendering process is totally the same as Scaffold-GS, with no extra time or memory consumption.

@smart4654154
Copy link
Author

thank
Are you saying that you have reduced the disk usage of the result files, but the space for data in VRAM and the VRAM used for rendering have not been reduced?

@YihangChen-ee
Copy link
Owner

Yes. We are doing storage compression, but not doing rendering efficiency. Storage compression can help with smaller storage usage and shorter transmission time.

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