Utilization in VO and SLAM

[JesseZZZZZ]

Hi! Thank you for your great work! I want to use it in my Visual Odometry task, as a tool to gain depth map from RGB input. So, I wonder whether Depth Anything can get the absolute depth, or does the relevant value of depth keeps the same for video input? For instance, if the camera circles a table, can the depth of the table in the depth map keeps stable?

Looking forward to your reply, and Thank you!