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

doubts about tracking #40

Open
JiePaiWs opened this issue Nov 12, 2024 · 1 comment
Open

doubts about tracking #40

JiePaiWs opened this issue Nov 12, 2024 · 1 comment

Comments

@JiePaiWs
Copy link

First, thank you for your work. I have some confusion about the tracking part in the paper. The paper presents L tracking, where the weight for the depth part is determined by the standard deviation, and the weight for the color part is controlled by λt. So, how does {R,t} influence L tracking, and why minimizing L tracking can optimize {R,t}? Does this {R,t} refer to the current frame or all sampled frames?

@eriksandstroem
Copy link
Owner

Hi!
Thanks and sorry for my late reply! Thanks for your question.

The {R, t} represents the pose ONLY of the current frame. We optimize the post of the current frame such that it renders a color and depth as close as possible to the sensor depth at the same frame. Does that help?

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