I am using your pretrained weights for the YCB dataset on my custom camera (Intel Realsense d415) stream/pictures but it seems that there is some kind of "shifting" applied to the objects (the orientation and size seem correct).
I have changed the K intrinsics and the factor depth to my camera.
Here you can see the best results I have managed to get for some objects but it's not accurate.
How can I improve the results? Do you have any suggestions?
Thank you very much for your time and consideration.
Hello @ethnhe ,
I am using your pretrained weights for the YCB dataset on my custom camera (Intel Realsense d415) stream/pictures but it seems that there is some kind of "shifting" applied to the objects (the orientation and size seem correct). I have changed the K intrinsics and the factor depth to my camera.
Here you can see the best results I have managed to get for some objects but it's not accurate.
How can I improve the results? Do you have any suggestions?
Thank you very much for your time and consideration.