As you claimed in paper "Lyra 2.0: Explorable Generative 3D Worlds":
"To construct the fine-tuning dataset, we autoregressively generate 3,000 one-minute videos using images and camera
trajectories from DL3DV [60]."
I'd like to know how to resolve the scale discrepancy between the camera poses in dl3dv and the camera paths in Lyra2. Is there a script available that can help us handle this?
As you claimed in paper "Lyra 2.0: Explorable Generative 3D Worlds":
"To construct the fine-tuning dataset, we autoregressively generate 3,000 one-minute videos using images and camera
trajectories from DL3DV [60]."
I'd like to know how to resolve the scale discrepancy between the camera poses in dl3dv and the camera paths in Lyra2. Is there a script available that can help us handle this?