Open hongsukchoi opened 2 years ago
Hi, hongsukchoi, we use the provided YCB CAD object models when testing object pose during inference. We project the mesh vertices onto the image to get key-points.
@stevenlsw
But the number of points is different. The original YCB CAD models have much more dense vertices and faces. How did you sample from them?
I download from here https://rse-lab.cs.washington.edu/projects/posecnn/, are you using the same source?
Oh, why are there different YCB object download links?
I used below link.
http://ycb-benchmarks.s3-website-us-east-1.amazonaws.com/
Thank you for your clarification.
Hi, your work is inspiring me a lot.
I found that you are using different a pointcloud from the original data for YCB objects. How did you get it?
Did you random sample from the original point cloud?