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

Add visualization #60

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Conversation

sorceressyidi
Copy link

  1. add visualization [render .pth into videos] as in https://github.com/hbb1/2d-gaussian-splatting
  2. add save ply as in https://github.com/graphdeco-inria/gaussian-splatting

cam.world_view_transform = torch.from_numpy(np.linalg.inv(c2w).T).float().cuda()
cam.full_proj_transform = (cam.world_view_transform.unsqueeze(0).bmm(cam.projection_matrix.cuda().unsqueeze(0))).squeeze(0)
cam.camera_center = cam.world_view_transform.inverse()[3, :3]
cam.timestamp =10.0/n_frames*i

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here the max timestamp value is hardcoded. This breaks other datasets which have a different scale(e.g dnerf with 0.0->1.0). I think you should be able to pass down the time_duration value from the config .yaml file

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for your review!
You’re absolutely right – I overlooked this point. I will make the necessary changes to pass the time_duration value from the config.yaml file instead of hardcoding the max timestamp.

Let me know if you have any further suggestions, and thanks again for your helpful feedback!

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

Successfully merging this pull request may close these issues.

2 participants