search

aofrancani / TSformer-VO

Implementation of the paper "Transformer-based model for monocular visual odometry: a video understanding approach".
https://arxiv.org/abs/2305.06121
MIT License
71 stars 11 forks source link

Reference Frame of the predicted poses #18

Open mohawk99 opened 6 months ago

mohawk99 commented 6 months ago

Hi,

So I want to make the model work for another dataset and wanted to know which frame the model predicts the poses in ? I'm assuming it's the camera frame i.e. it takes the first image as it's origin?

Also if you could tell me what would I need to change in order to customize the model for another dataset i.e. other than coordinate frames and preprocessing steps.

Thanks!