Skip to content

Regarding my weird use case #100

Description

@filelele

Thanks for your public work.

I want to ask how robust the model if I use it this way:

  1. Carefully precapture N frames of a bounded scene, cover everything in that scene.
  2. Frames are captures in a way that there is good amount of overlap between t-1 and t.
  3. Use Direct Mode, set keyframe_interval = 1 so all these N frames get its full KV cache stored.
  4. New frame arrives (Let call it Query frame), taken from random position of the scene, not overlap with the last frame t_N of N frames above, but definitely overlap with at least one of them.
  5. Get the Camera Pose of Query frame.

In short, I want to use lingbot-map purely as Visual Localization. Will using it that way degrade performance too much?

As I understand it will lose the Local Pose-reference Window advantage, where the overlap of Query frame is with somewhere in the N frames of KV cache, but in this case not with the latest frame t_N, so the time order is messed up.

I tested that way of use, and the camera pose seems quite good to my human eyes, but I dont have a way to measure it exactly in metric.

Thanks for reading.

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