Closed kiwiwan closed 1 year ago
Hi, please try some other objects that have no transparency. The bottle shown in the figure is a bit transparent and the depth is usually bad in this case. We do not calibrate the realsense.
We have no idea about that. But you should use the intrinsics of the RGB camera after you align the depth, otherwise there will be some offsets for the pointcloud, resulting in offsets in the detected grasp poses.
Yes, 1280x720 means there are more points in the point cloud. We also use 1280x720.
I have 3 problem in my testing for anygrasp_sdk using a realsense d435i. I hope you can help me with these questions. Thanks!