kaolin-wisp
kaolin-wisp copied to clipboard
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
Support 2d images and textures in the interactive renderer scene graph. This allows to visualize them together with neural fields.
A fix for hashgrid grad by coords not being passed back from backward kernel. See discussion in issue #142
During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/khurram/kaolin-wisp/app/nerf/main_nerf.py", line 488, in app.run() # Run in interactive mode File "/home/khurram/kaolin-wisp/wisp/renderer/app/wisp_app.py", line 253, in...
Below is an example of a comparison of gradient returned by tinycudann vs numerical gradients computed for a simple field based on hash grid. The difference between the two approaches...
New to this library, can use some guidance here. I have a dataset created using [colman script](https://github.com/NVlabs/instant-ngp/blob/master/scripts/colmap2nerf.py). How to best train/load/save model so that I can query it to get...
Hi, I would like to use the acceleration structures of kaolin-wisp for 2D data (180 000 points per sample). What do I need to change in the pipeline to make...
Thanks again for the amazing library! I've been using it with other students for a project for my master degree. The problem is that as it's usual for students, we...
WispApp uses glumpy with a `glfw_imgui` backend, which defaults to OpenGL 2.1 context. However, imgui expects an OpenGL 3.3+ context, which causes errors on some envs. 1. This MR creates...
This might be more of an OpenGL setup issue, but it's only occuring for the interactive rendering. I can use the nerf app fine in headless mode, but when I...