Some question about BA

[gwxxx]

I wonder if I use VGGT+BA, whether depth map and point map will be refined?

[jytime]

Hi, we mainly used BA for refining the camera poses. Specifically, when applying BA, we select a set of 3D points and construct their corresponding tracks. We then jointly optimize these 3D points along with the camera poses, i.e. traditional BA process. During this optimization, the point map (or depth map) is also refined, but only sparsely—for example, approximately 2k points.

[stalkerrush]

Hi @jytime , would it be possible to release the inference code with BA? It would be super helpful even if it's not well-organized :)

[jytime]

According to the recent feedback, it seems the community does have some interest in this. I'll consider it depending on my bandwidth.

[jytime]

Closing this issue as the BA code has been uploaded.