Generating Video Following having One Test Image

[hmdolatabadi]

Hi,
Thanks for the cool work.

I have a question regarding your test script.
In Figure 2 (the test phase), it seems like the video is going to be entirely generated by having one input image.
In the code, however, you compute the trajectory using the ground-truth video.

VideoAutoencoder/test_re10k.py

Lines 102 to 103 in dc1aa14

	clip_in = torch.stack([clip[scene_index], clip[i+1]])
	pose = get_pose_window(encoder_traj, clip_in)

Is there some point that I am missing? And is generating a video having only one fixed image possible?
(I know that for training you would necessarily need a video sequence, what I mean is at test time.)

Thanks.