Closed lemyanh2612 closed 1 year ago
Thanks for your interest in our work. In this work, we mainly focused on static images and not videos, although it may be possible to extend this for videos. Are you interested in training DETReg on videos or just running inference on video?
The most naive idea would be to perform video colorization then run the system as is.
Could you provide me some feedback about this possibility and some guidance on where is the video custom data loading actually happening so that I could check?
Thank you for your time