Michel Zeller
Michel Zeller
@nikitakaraevv Thank you for the speedy reply! I guess I'll continue with the regular CoTrackerPredictor if there is no easy "hacky" solution in that case :-)
(BTW: the variables W and H are not initialised in the case of `is_first_step=True` and `queries is not None` in the online predictor --> small bug) ```python if is_first_step: self.model.init_video_online_processing()...
The same thing just happened to me. I also just captured a short video w/ my phone. After processing the data, my camera model is `'SIMPLE_RADIAL'`. I'm using the following...
Any update on this?
I'd also be interested in this code; specifically to be able to provide known camera intrinsics to the pipeline. I assume this additional prior should simplify the optimization procedure as...