Skip to content

Why is camera coordinate data passed to SMPLLoss during computing MotionLoss? #51

Open

Description

@linjiangya

Dear authors,

In SmoothOptimizer and RootOptimizer, I think the joints3d/joints3d_op in SMPLLoss/RootLoss is in the world coordinate system. And the re-projection is performed to get the proj_2d joints from (world -> pixel coordinates).

However, it seems like in MotionLoss, the cam_pred_data is passed into RootLoss:

loss, stats_dict = super().forward(
observed_data, cam_pred_data, nsteps, valid_mask=valid_mask
)

Whilst I think from the logic in rollout_latent_motion(), it looks like cam_pred_data is actually still in the world coordinate system, and is transformed back from the local coordinate system used in the rollout procedure. I am therefore confused about the name of the variables: Why is this data named cam_pred_data with a comment above saying "must return trans and root orient in camera frame...", while the function name is apply_world2prior? And it doesn't look like camera coordinate system data to me.

I just would like to confirm whether this is a naming issue or I misunderstood it. Thank you!

Activity

  1. changed the title [-]Why is camera coordinate system used in MotionLoss?[/-] [+]Why is camera coordinate date passed to SMPLLoss during computing MotionLoss?[/+] on Feb 20, 2024
  2. changed the title [-]Why is camera coordinate date passed to SMPLLoss during computing MotionLoss?[/-] [+]Why is camera coordinate data passed to SMPLLoss during computing MotionLoss?[/+] on Feb 20, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions