2D joints from 3D prediction about vibe HOT 6 CLOSED

Hi @kallivad,

You can check this projection function:

For a sample usage, check this:

from vibe.

I am closing it now, feel free to ask if you need help about it.

from vibe.

Hey! I'm trying to get 2D pose from VIBE Output. How do I use the perspective projection function to do this? What inputs should I pass?

from vibe.

Same question.
For function "perspective_projection(points, rotation, translation,focal_length, camera_center)"
How to calculate Camera rotation、Camera translation、Focal length、Camera center

from vibe.

For classical intrinsic and extrinsic matrix, the following solution works well.

cam = dicts['orig_cam']
cam_s = cam[0:1]
cam_pos = cam[2:]
flength = w / 2.
tz = flength / (0.5 * w * cam_s)
trans = -np.hstack([cam_pos, tz])
camera_data['color_focal_length'].append(np.array([w / 2, w / 2]))
camera_data['color_center'].append(np.array([[w / 2, h / 2]]))
camera_data['c2w'].append(np.eye(4))
camera_data['c2w'][:3,3] = trans

from vibe.

For classical intrinsic and extrinsic matrix, the following solution works well.

cam = dicts['orig_cam']
cam_s = cam[0:1]
cam_pos = cam[2:]
flength = w / 2.
tz = flength / (0.5 * w * cam_s)
trans = -np.hstack([cam_pos, tz])
camera_data['color_focal_length'].append(np.array([w / 2, w / 2]))
camera_data['color_center'].append(np.array([[w / 2, h / 2]]))
camera_data['c2w'].append(np.eye(4))
camera_data['c2w'][:3,3] = trans

I found the cam params converge worse, and i use weak perspective in my code, in which kpy_2d = scale(kyp3d[, :2] + txy ). I think the key reason is the focal length of the dataset is different with each image, and it range from 400 mm to 800 mm. So maybe the network cannot regress the scale well?
As "It is common to assume a fixed focal length to perform perspective projection. " . I wonder if the performance would be improved if i use perspective projection instead of weak perspective?

from vibe.