-
Notifications
You must be signed in to change notification settings - Fork 16
New issue
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
Visualize trained plenoxels #19
Comments
For completeness, I'll also share my code for loading the model. I moved some of the functions to a jupyter notebook to keep the evaluation code disentangled from the training code.
having defined these, I
|
# for free
to join this conversation on GitHub.
Already have an account?
# to comment
Hi
I would like to visualize one of your trained plenoxels. Ideally, I would want to just load a ckpt and render views from a spherical path around the center object. I would like to be able to do this without having to download co3d. However, I find this challenging to do with your current code.
I was able to load your model by using your
on_load_checkpoint
that dequantize the checkpoints and load the model. Then I want to render views from this.I decide on an intrinsic matrix:
and use your function
spherical_poses
to get the extrinsicsI then try to create the rays from the first pose using various of your functions
and then try to render
but when I visualize the rendering it looks like I did something wrong:
Could you please help me? Would be very useful to check that the model loading is correct and to see how good the reconstructions are.
The text was updated successfully, but these errors were encountered: