NVlabs / CenterPose

Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022)
Other
285 stars 34 forks source link

Number of objects of interest in a single image for training and inference #24

Closed monajalal closed 6 months ago

monajalal commented 7 months ago

As for training and inference, does it matter if I have more than one instance of a class ("chair") in one image or do you expect single appearance of the object of interest in a single image? Same question for inference.