Open resurgo97 opened 1 month ago
For the record, I tried to incorporate known camera poses before shifting the camera along z-axis (in order to disentangle scale & focal length from extrinsic matrix), but it failed.
Hi, are you having any progress in developing preset known poses with sparse_global_alignment? I'm working on the same issue...
Hi, are you having any progress in developing preset known poses with sparse_global_alignment? I'm working on the same issue...
Unfortunately not ;( I think the current implementation is not fundamentally appropriate for known camera pose scenarios. If you're running it only for inference, fastest way seems to be starting from the DUSt3R code (which is entirely different from MASt3R code) and modify it to add additional heads that were added in MASt3R.
Have you tried modify logic of function make_K_cam_depth
then run sparse_alignment to optimize depthmaps?
I think it is easy to pass some known camera poses to setting. During the optimization, the fixed poses are not passed to the optimizer, that would be OK.
I'm seeking a way to run global alignment optimization with known camera poses. After examining the code, I've identified some challenges:
cam2w
matrices are constructed inmake_K_cam_depth
, but they don't directly correspond to standard extrinsic matrices.The code handles scale ambiguity by adjusting the translation vector based on focal length and scale, rather than multiplying scales to the pointmaps.
This approach leverages the fact that scaling up the pointmap is equivalent to: a) increasing the focal length b) shifting the camera location along the z-axis
As a result, when mapping 2D points into 3D space, per-frame scales don't need to be multiplied to depthmaps:
While this implementation is convenient, it makes incorporating known camera poses challenging because
cam2w
is not a pure extrinsic matrix and is entangled with the focal length (an intrinsic parameter).Questions
I welcome any opinions or insights on this topic from other people.
Thank you!