Shawn Zhuang

Poor performance on fast-moving data & inconsistent orientation on constant pose estimations

5

Hello, I've noticed that the tracking performance seems to deteriorate with fast motion as shown in this video, even after raising my `track_refine_iter` to 100: https://github.com/NVlabs/FoundationPose/assets/60201722/e31a292f-85ba-40f2-8a5b-df9922d07598 I have a workaround...

Could not create GL context

2

Hi! I'm in docker/Ubuntu 20.04 and I ran the following: ``` python bundlesdf/run_nerf.py --ref_view_dir /home/donghun/Documents/FoundationPose/ref_views_16 --dataset ycbv ``` And I'm getting the below error: ```(my) root@donghun:/home/donghun/Documents/FoundationPose# python bundlesdf/run_nerf.py --ref_view_dir /home/donghun/Documents/FoundationPose/ref_views_16...

Is there a guideline on how to get these two pieces of data for the reference images?