very interesting work, the output is very clean how does it deal with lens distortion? is it compensated by the FBA where the sample with the least distortion gets chosen as the reference? or does the FBA internally have some estimation of the distortion and applies that to all keypoints from the same sample?
![[ECCV 2024] GeoCalib: Learning Single-image Calibration with Geometric Optimization](http://i.ytimg.com/vi/uOmTwvKreM4/mqdefault.jpg)
![[ECCV 2024] GeoCalib: Learning Single-image Calibration with Geometric Optimization](/img/tr.png)
![[CVPR 2021] Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](http://i.ytimg.com/vi/vPkXhKQn2oI/mqdefault.jpg)
Can't wait to see a software implementation of this!
very interesting work, the output is very clean
how does it deal with lens distortion? is it compensated by the FBA where the sample with the least distortion gets chosen as the reference? or does the FBA internally have some estimation of the distortion and applies that to all keypoints from the same sample?
Excellent work!
awesome work😃
WOW!!! I will be shocked if they did not give you the Marr prize.
6啊老铁
Awesome work!