You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
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?
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?
The text was updated successfully, but these errors were encountered: