Matthew Tancik

Just checking, everyone in this thread is able to see the dataset images, just not the render (same as in the image in the original post)?

Sorry this is proving to be such an issue. It seems that webrtc initial connection is sometimes flaky. We we continue to try to debug this, unfortunately it isn't something...

A fix to this was merged in #741. You will need to clone the repo for this fix, it is not yet in the pip package.

The keyboard controls are great! The mouse controls seem to have changed though, they don't mimic what was existing in the main branch.

> They arn't reversed. Rather the pivot point seems to be at the camera and moving side-to-side is very slow (which might be related). In the example video, this PR...

This looks like an issue with installing tiny-cuda-nn. You could try installing a local clone of the tcnn repo, ``` git clone https://github.com/NVlabs/tiny-cuda-nn.git cd bindings/torch python setup.py install ``` If...

I think this may have emerged with the recent `instant_ngp` implementation updates. Maybe @liruilong940607 has some ideas?

NGP training works for me. Oddly it only fails for me when I don't run with the debugger. I think Ethan is also has seen this segfault. I'll try to...

Hmmm, even more mysterious. Doesn't seem tied to a commit, I tried going back pretty far, and this only became an issue in the last week or so. Maybe some...

I think all outputs that are images [HxWxC] should be sent to the viewer regardless of the channel dimensions. The viewer should have logic to determine the way to visualize...