Closed junhua-l closed 1 year ago
Since Figure 5 in the article also shows the visualizations of point clouds with different training iterations, I guess there are some ways to derive the point cloud.
parser.add_argument("--save_iterations", nargs="+", type=int, default=[2000, 3000, 5000, 7_000, 9000, 10000,12000, 14000, 20000, 30_000, 45000, 60000])
output/your_checkpoint_dir
P.S: I visualized results in Blender(Open3D also works)
Sorry for disturbing you again. That's not what I'm looking for.
What you provide is to store the static point cloud on different training iterations. Since this is a dynamic Gaussian, what I want is the point cloud of each frame when the dynamic Gaussian is played after training.
I have modified a version myself and it has worked now. Thank you for your answer : )
@JunhuaLiu0 could you share your modification?
I have modified a version myself and it has worked now. Thank you for your answer : )我自己修改了一个版本,现在已经可以运行了。谢谢您的回答 : )
@junhua-l could you share your modification? Or can you provide some hints? Thank you
Thanks for the great work.
I now want to export the contents of each frame for editing. The output of Siggraph 2023 3D Gaussian is a.ply file, and I can easily get the corresponding point cloud and mesh. For 4D Gaussian, I want to know how to get the deformable position of 3D Gaussian in each frame so that I can output the per-frame point cloud or mesh.
Any possible advice or practice would be very helpful to me. Thank you sincerely.