What does HackerNews think of instant-ngp?

Instant neural graphics primitives: lightning fast NeRF and more

Language: Cuda

#17 in Machine learning
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields | Jun 2023
Expand Context ↕
instant-ngp ([1]) from NVIDIA can render NeRF in VR in real-time, assuming a very good desktop video card. Note that instant-ngp is not as photo-realistic as Zip-NeRF. But it's still very good!

1. https://github.com/NVlabs/instant-ngp
HDR-NeRF: High Dynamic Range Neural Radiance Fields | Apr 2023
Expand Context ↕
Check out https://github.com/NVlabs/instant-ngp.

Trains a nerf in a couple of seconds.

I went on a trip to Italy last year and took a video while walking around Michelangelo’s David. Even with that relatively poor image quality this let me turn it into a pretty high quality nerf.
Try Stable Diffusion's Img2Img Mode | Aug 2022
Expand Context ↕
https://github.com/NVlabs/instant-ngp
Photogrammetry Guide | Jul 2022
Expand Context ↕
In my experience NeRF tends to work better for objects that photogrammetry struggles with, like transparent objects. By using marching cubes you can also export scenes as a mesh. instant-ngp (https://github.com/NVlabs/instant-ngp) has done an amazing job of making NeRF accessible, but you still need camera positions from other software such as COLMAP.
Direct Voxel Grid Optimization | Jun 2022
Expand Context ↕
instant-ngp: https://github.com/NVlabs/instant-ngp
Nvidia Research Turns 2D Photos into 3D Scenes in the Blink of an AI | Mar 2022
This is great, and the paper+codebase they're referring to (but not linking, here [1]) is neat too.

The research is moving fast though, so if you want something almost as fast without specialized CUDA kernels (just plain pytorch) you're in luck: https://github.com/apchenstu/TensoRF

As a bonus you also get a more compact representation of the scene.

[1] https://github.com/NVlabs/instant-ngp

Nvidia Research Turns 2D Photos into 3D Scenes in the Blink of an AI | Mar 2022
Expand Context ↕
Still, NVIDIA's achievement (and Thomas Müller in particular) is amazing. Thomas and his collaborators achieved an almost 1000x performance improvement, by a combination of algorithmical and implementation tricks.

I highly recommend trying this at home:

https://nvlabs.github.io/instant-ngp/

https://github.com/NVlabs/instant-ngp

Very straightforward and gives better insight into what NeRF is than any shiny marketing demo.