Skip to content

No metadata handoff when undistorting cameras #3721

@azzarelli

Description

@azzarelli

Hi, just working on some slightly overly complex data parsing and came across the undistortion functionality in the dataloading script and I was wondering if there was a reason why the metadata does not get passed through?

new_camera = Cameras(
camera_to_worlds=camera.camera_to_worlds.unsqueeze(0),
fx=torch.Tensor([[float(K[0, 0])]]),
fy=torch.Tensor([[float(K[1, 1])]]),
cx=torch.Tensor([[float(K[0, 2])]]),
cy=torch.Tensor([[float(K[1, 2])]]),
width=torch.Tensor([[image.shape[1]]]).to(torch.int32),
height=torch.Tensor([[image.shape[0]]]).to(torch.int32),
)

Ideally, I'd like to pass in metadata to load small texture images on the fly (independent of training), which I thought I could pass through the Cameras() objects so was trying to do this through the camera class

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions