facebookresearch / vggsfm

VGGSfM: Visual Geometry Grounded Deep Structure From Motion
Other
938 stars 72 forks source link

A problem about the camera scale xyz #87

Open xinfeixiang1 opened 3 days ago

xinfeixiang1 commented 3 days ago

Thanks for your great work.

However, in our practical tests (where the input is a video), we found that the camera's position in space was normalized to a range with a diameter of 6, regardless of whether the camera was moving closer to or longer in space. This does not align with the actual scale of the camera's position. Could you please advise on how to resolve this issue?

Thank you very much.

jytime commented 2 days ago

Hi @xinfeixiang1 ,

Are you aiming to reconstruct the scene at a real-world scale? Unfortunately, this isn’t feasible with structure from motion (SfM), as it inherently produces scale-agnostic reconstruction. If accurate scale is crucial, you could introduce additional references, such as known size of an object, to calibrate the SfM output to real-world dimensions.

Regarding camera motion, it can only be understood relatively through SfM. For example, you can determine that one camera position is 10% closer to an object compared to another, but you won’t be able to quantify the exact distance in meters.