From the existing documentation, it appears that the camera extrinsics are in OpenCV convention (x, -y, -z) or (right, down, into the scene) and are in world-to-camera (w2c) format. Is this right?
I tried warping a frame from the apple scene to the other viewpoint using the depth given. Can you help me with the details? Should the depth be scaled?
The warped frame is not matching the second frame. I used this code to warp the frame.
I read the data as follows:
camera_params = read_json(camera_params_path)
focal_length = camera_params['focal_length']
principal_point = camera_params['principal_point']
intrinsic = numpy.eye(3)
intrinsic[0, 0] = focal_length
intrinsic[1, 1] = focal_length
intrinsic[0, 2] = principal_point[0]
intrinsic[1, 2] = principal_point[1]
rotation_matrix = numpy.array(camera_params['orientation'])
translation_vector = numpy.array(camera_params['position'])
extrinsic = numpy.eye(4)
extrinsic[:3, :3] = rotation_matrix
extrinsic[:3, 3] = translation_vector
warper = Warper()
frame1 = warper.read_image(frame1_path)[:, :, :3]
frame2 = warper.read_image(frame2_path)[:, :, :3]
depth1 = warper.read_depth(depth1_path)[:, :, 0]
warped_frame2 = warper.forward_warp(frame1, None, depth1, extrinsic1, extrinsic2, intrinsic1, intrinsic2)[0]
The frames look like below.
From the existing documentation, it appears that the camera extrinsics are in OpenCV convention
(x, -y, -z)or(right, down, into the scene)and are in world-to-camera (w2c) format. Is this right?I tried warping a frame from the apple scene to the other viewpoint using the depth given. Can you help me with the details? Should the depth be scaled?
The warped frame is not matching the second frame. I used this code to warp the frame.
I read the data as follows:
The frames look like below.
