-
Notifications
You must be signed in to change notification settings - Fork 227
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
To get cam_intrinsics and cam_extrinsics from .npz files #300
Comments
Hi, @MoyGcc ROMP/simple_romp/romp/utils.py Line 331 in 91dac01
It take the estimated 3D joints, the 2D joints pj2d_org, image size, and the focal length to estimate the corresponding 3D translation in the camera space defined by these intrinsice paramters. In BEV, we calculate the focal length like this: focal length: when FOV=60 deg, 443.4 = H/2 * 1/(tan(FOV/2)) = 512/2. * 1./np.tan(np.radians(30)) BEV takes the square 512 x 512 input, we assume the FOV = 60 degree |
Have you solved this problem? I met the same issue. |
Hi Yu @Arthur151, ROMP/simple_romp/evaluation/eval_AGORA.py Line 79 in 91dac01
and now the projected smpl mesh can align well with the image. Though there is still a "slight" difference (below, the one with normal color is my projected result) in terms of the projection. I think it's okay. @hongsiyu, you could probably also refer to the evaluation on the AGORA dataset for doing this. |
That's clever. Glad to hear that. |
So the intrinsic is ([443.4, 1, 512//2], [1, 443.4, 512//2],[0, 0, 1]), and the extrinsics[:3, 3] = cam_trans , right? @MoyGcc |
I followed the way you mentioned with my own video. But the progress image in humannerf seems not correct. Do you succeed in trainiing humannerf with AGORA dataset. |
@Andyen512
|
Thank you very much, the focal length makes me succeed in training humannerf. |
@Arthur151 Sorry, why using the humannerf cam_intrinsics? I was using Line 60 in 91dac01
I was so confused. |
@Andyen512 To inference on you own video, you can re-calculate the focal length : |
ok thx, I'll try |
hi @hongsiyu , can you tell me how to use ROMP to obtain "3x3" cam_intrinsics and "4x4" cam_extrinsics, thanks. |
Hi Yu, thanks for your work and such an organized repo!
I'm now using ROMP to get SMPL poses and would like to visualize the meshes via a perspective camera. I usually use a similar way as chungyiweng/humannerf#1 to convert the
s
,t_x
, andt_y
along with a human bbox to the pinhole camera parameters and it does work on VIBE output. However, it seems like I cannot easily get the parameters with the output from ROMP .npz outputs (I can get a rough bbox frompj2d_org
). I found that the scaling factors
is quite different between the VIBE and ROMP estimation for the same input image (~1.14 in VIBE and ~0.58 in ROMP). Could you please point out how I can quickly obtain (estimate) the camera intrinsic and extrinsic? Thanks!The text was updated successfully, but these errors were encountered: