Skip to content

Details about the 3D Reconstruction Finetune dataset. #62

Description

@junaoshen

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?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions