search

gengshan-y / rigidmask

Code for "Learning to Segment Rigid Motions from Two Frames". CVPR 2021.
https://gengshan-y.github.io/rigidmask/
MIT License
188 stars 18 forks source link

Kitti Inference #10

Open cbiras opened 2 years ago

cbiras commented 2 years ago

Hello! I was wondering how was the calibration file constructed, for the kitti video example. I am trying to run the model on other kitti videos, but the calibration files are looking entirely different. Thank you!

gengshan-y commented 2 years ago

Hi, the calibration format is follows $seqname=name-of-image-folder $seqname-calib.txt

f1, pxn,pyn
...
fn, pxn,pyn

fn is the focal length of n-th image pxn and pyn are the x,y principal point of the n-th image.

We assume square pixels where fx=fy and skew=0.