kaolin-wisp icon indicating copy to clipboard operation
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).

Results 56 kaolin-wisp issues
Sort by recently updated
recently updated
newest added

Support 2d images and textures in the interactive renderer scene graph. This allows to visualize them together with neural fields.

feature

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...

bug

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...

bug

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...

good first issue

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...

documentation

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...

bug

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...

setup