You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I try to install the nerfstudio in your repo, but the requirements for torch and cuda might be old, and I cannot successfully install tiny-cuda-nn for it. So the older version cannot run.
So I install the latest nerfstudio, and it can run as well, except the viewer's camera updating logics, because the code ViewerState in nerfstudio has changed so much. I haven't found a proper way to update the cameras till now.
The text was updated successfully, but these errors were encountered:
Sounds about right, I had seen that they made a lot of changes to the viewer. Updating the poses dynamically has been a challenge for a while, and I've brought it up to the Nerfstudio team but it's not a priority feature for them. I'll be working on transitioning to ROS2 this week, and so I'll try to poke around in the Viewer code and see if I can fix this issue there.
@elenacliu Check out commit 0fc928d. This should allow the camera positions to populate over time if you refresh the page. I've tested this on my setup and v0.3.3 of nerfstudio. It seems like the nerfstudio team is doing yet another viewer overhaul so I probably won't explore this problem anymore until that is finished.
I try to install the nerfstudio in your repo, but the requirements for torch and cuda might be old, and I cannot successfully install tiny-cuda-nn for it. So the older version cannot run.
So I install the latest nerfstudio, and it can run as well, except the viewer's camera updating logics, because the code
ViewerState
in nerfstudio has changed so much. I haven't found a proper way to update the cameras till now.The text was updated successfully, but these errors were encountered: