Closed mhaboali closed 4 years ago
Hi @mhaboali !
Currently the models only work on the specific datasets (note that object pose estimation is instance-specific in our case, so the model needs to see the CAD model of the object at train time). For results on a new dataset you might be interested in our previous work https://github.com/hassony2/obman_train (you can try the video demo)
Cheers !
Yana
Hi, thanks for sharing this great project!
I'm wondering if it's possible to run a live demo using the D435i camera or this library works only with specific datasets?
Thanks!