instant-ngp
nerf-pytorch
Our great sponsors
instant-ngp | nerf-pytorch | |
---|---|---|
147 | 3 | |
15,155 | 4,936 | |
2.1% | - | |
7.5 | 0.0 | |
about 2 months ago | 3 months ago | |
Cuda | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
instant-ngp
-
Mind-blowing results (LORA/Checkpoint mix)
This is really cool! Could you now use something like this to turn the new images in a 3d model? Or even use open pose (controlnet) to generate a bunch of images from different angles and use InstantNeRF to make a 3d model for free!
-
[D] NeRF, LeRF, Prolific Dreamer, Neuralangelo, and a lot of other cool NeRF research
[Code] https://github.com/NVlabs/instant-ngp
[Project Page] https://nvlabs.github.io/instant-ngp/
-
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
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!
-
Do you think neural rendering ready in production?
We know that a lot of project with NERF, include (instant-ngp) https://github.com/NVlabs/instant-ngp or kaolin-wisp (https://github.com/NVIDIAGameWorks/kaolin-wisp)
-
I know reflective surfaces are a no go, but how can this be done? 2 pics are from Metashape and 2 are from RC. Zero are good enough.
https://developer.nvidia.com/blog/getting-started-with-nvidia-instant-nerfs/ https://github.com/NVlabs/instant-ngp
Try using NeRFs like: - Lumalabs AI: https://lumalabs.ai/ - Nerfstudio (google colab or download it) - Nvidia instant NeRFs: https://github.com/NVlabs/instant-ngp
- NVIDIA NeRF installation?
-
How to create virtual view/360 type view from known cameras?
I'd recommend starting with NVIDIA's "Instant Neural Graphics Primitives": https://github.com/NVlabs/instant-ngp because it trains the NeRF in seconds (it sped up the state of the art by like 10,000x. It's insane fast)
-
Game development is about to go wild with AI
There is https://github.com/NVlabs/instant-ngp that can do it.
nerf-pytorch
-
[D] Something basic I don't understand about Nerfs
Found relevant code at https://github.com/yenchenlin/nerf-pytorch + all code implementations here
-
helpful pointers to state-of-the-art material for depth estimation from multi-view videos captured from cameras with arbitrary poses.
I have been curious about NeRF and have tried out the software. I really like the idea, but I have found generating the NeRF representation to be too slow and does not do seem to do too well if the number of cameras in the rig are a bit sparse. I have seen that there have been some evolution and variations of the NeRF concept and I am looking into some of them currently.
-
[P] Minimal PyTorch implementation of NeRF. Full model implementation and training code in 320 lines.
While there are other PyTorch implementations out there (e.g., this one and this one), I personally found them somewhat difficult to follow, so I decided to do a complete rewrite of NeRF myself. I tried to stay as close to the authors' text as possible, and I added comments in the code referring back to the relevant sections/equations in the paper. The final result is a tight 374 lines of heavily commented code (320 sloc—"source lines of code"—on GitHub) all contained in a single file. For comparison, this PyTorch implementation has approximately 970 sloc spread across several files, while this PyTorch implementation has approximately 905 sloc. A Colab notebook for the full model can be found here.
What are some alternatives?
awesome-NeRF - A curated list of awesome neural radiance fields papers
tiny-cuda-nn - Lightning fast C++/CUDA neural network framework
TensoRF - [ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields
colmap - COLMAP - Structure-from-Motion and Multi-View Stereo
instant-meshes - Interactive field-aligned mesh generator
instant-ngp-Windows - Instant neural graphics primitives: lightning fast NeRF and more
nerf - Code release for NeRF (Neural Radiance Fields)
svox2 - Plenoxels: Radiance Fields without Neural Networks
Meshroom - 3D Reconstruction Software
agi2nerf - Simple tool for converting Agisoft XML files to NERF JSON files for https://github.com/NVlabs/instant-ngp
stable-diffusion-webui - Stable Diffusion web UI
frigate - NVR with realtime local object detection for IP cameras