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

About the Depth #30

Open
jypjypjypjyp opened this issue Nov 12, 2024 · 0 comments
Open

About the Depth #30

jypjypjypjyp opened this issue Nov 12, 2024 · 0 comments

Comments

@jypjypjypjyp
Copy link

jypjypjypjyp commented Nov 12, 2024

Hello, I've noticed that the calculation of the center of the Gaussian (mean) in the code is achieved by multiplying the direction by the depth.

origins, directions = get_world_rays(coordinates, extrinsics, intrinsics)
means = origins + directions * depths[..., None]

However, this is different from what I consider as depth. As shown in the figure below, I think the depth is the distance from the image plane to the camera (Z).
image

When I was running some experiments, I found that for the flat objects on the depth map, the point cloud according to the Gaussian center points showed an obvious curvature.
image
image
image

May I ask if this result is correct?

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

1 participant