[HN Gopher] Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fi...
___________________________________________________________________
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Author : netuffresche
Score : 51 points
Date : 2023-06-06 06:32 UTC (16 hours ago)
(HTM) web link (jonbarron.info)
(TXT) w3m dump (jonbarron.info)
| Y_Y wrote:
| Where's the damn code?
| esafak wrote:
| https://paperswithcode.com/paper/zip-nerf-anti-aliased-grid-...
| lairv wrote:
| Another recent cool work in this field is this paper :
| https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/
|
| They manage to get the same quality, with <1hr of training, and
| running at 60fps 1080p, it uses point cloud instead of volumetric
| representation
| IshKebab wrote:
| Very impressive! How far are we from having this sort of thing in
| VR? The paper says the model render time was 0.9s which I guess
| means very far if that is per frame?
| krasin wrote:
| 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
| xrd wrote:
| I've been fascinated by NeRFs for a few years.
|
| But, there are really no viable models that run on consumer
| hardware like llama or stable diffusion.
|
| Or, am I wrong? NeRF Studio seems promising but never works on my
| 6GB nvidia.
|
| I would really like to find a way to interpolate between two
| images using a NeRF (get the hallucination of the "image in
| between").
|
| Is there such a thing out there?
| dheera wrote:
| I don't know about 6GB but if you have a 12GB or 16GB card you
| should be able to run the vast majority of NeRF work out there,
| most of it is designed to run on a single GPU.
| riotnrrd wrote:
| I mostly have experience with Instant NGP, and it should work
| on older consumer NVIDIA cards. Their github page calls out
| Pascal cards as working, for example. 6 GB isn't much memory,
| though, so you may be limited in final resolution of the latent
| model and thus of the output.
| djsavvy wrote:
| I'm not sure I understand what this does --- what are the inputs
| and outputs?
| krasin wrote:
| The inputs are just photos from different positions. Then a
| neural net is trained so that you can ask to render a photo
| from any pose (including unseen).
|
| This particular work (Zip-NeRF) builds on top of the original
| NeRF paper: https://www.matthewtancik.com/nerf (the website has
| a good explanation what NeRF aka Neural Radiance Fields are)
| yarg wrote:
| This is amazing, but...
|
| It feels too damned clean, and I'm not sure its just the weirdly
| alien camera stability.
___________________________________________________________________
(page generated 2023-06-06 23:00 UTC)