TorchSharp
nerfstudio
TorchSharp | nerfstudio | |
---|---|---|
5 | 10 | |
1,254 | 8,569 | |
4.0% | 3.1% | |
9.5 | 9.6 | |
5 days ago | 5 days ago | |
C# | Python | |
MIT License | Apache License 2.0 |
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.
TorchSharp
- AI .NET
-
Machine learning with NET
There exist TorchSharp that is a С# wrapper around the same libtorch.dll that is wrapped by Python code in PyTorch, https://github.com/dotnet/TorchSharp. Though I don't know how exhaustive it is.
-
When the client's management is happy but their dev team is a pain
https://github.com/dotnet/TorchSharp here you go.
-
Does anyone actually use ML.NET?
With TorchSharp, you have access to libtorch in .NET, the library that powers PyTorch. This is what's currently backing the Text Classification API
-
.NET Core
In Artificial Intelligence Series-Overview
TorchSharp is a .NET library that provides access to libraries that support PyTorch. (Github https://github.com/xamarin/TorchSharp)
nerfstudio
-
Smerf: Streamable Memory Efficient Radiance Fields
You’re under the right paper for doing this. Instead of one big model, they have several smaller ones for regions in the scene. This way rendering is fast for large scenes.
This is similar to Block-NeRF [0], in their project page they show some videos of what you’re asking.
As for an easy way of doing this, nothing out-of-the-box. You can keep an eye on nerfstudio [1], and if you feel brave you could implement this paper and make a PR!
[0] https://waymo.com/intl/es/research/block-nerf/
[1] https://github.com/nerfstudio-project/nerfstudio
- Researchers create open-source platform for Neural Radiance Field development
-
first attempt to photogrammetry using DJI mini 2 and metashape. 460 images manual. What did I do wrong? What can i do to improve it? Would appreciate all kinds of advice to a newbie
Try rendering NERFs with your footage, you're gonna love the result and NERFs are pretty robust to reflections. You can use your Metashape solve for Nerf Studio https://github.com/nerfstudio-project/nerfstudio
-
What is the best way to create a dataset for NeRF?
Beyond these tips, I don't have much. There's lots of research about how to improve quality of solves in the software itself. I'm hoping these get added to instant-ngp, since it's fast and free, but it is research software, not a product, so we'll see. Another thing to maybe look at is Nerfstudio. It can use instant-ngp as a solver, but there are other solvers. I briefly tried it but couldn't figure out how it worked, from the small bit of time I spent with it. I hope to get back to it.
- Nerfstudio – A collaboration friendly studio for NeRFs
- When the client's management is happy but their dev team is a pain
- A collaboration friendly studio for NeRFs
-
NeRF ➜ point cloud export — now available via nerfstudio
nerf.studio | github | discord
- Show HN: A collaboration friendly studio for NeRFs
What are some alternatives?
TensorFlow.NET - .NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.
multinerf - A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
NumSharp - High Performance Computation for N-D Tensors in .NET, similar API to NumPy.
sdfstudio - A Unified Framework for Surface Reconstruction
TensorFlowSharp - TensorFlow API for .NET languages
smerf-3d
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
vision_transformer
DotMLBooks
kaolin-wisp - NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
ParquetSharp.DataFrame - ParquetSharp.DataFrame is a .NET library for reading and writing Apache Parquet files into/from .NET DataFrames, using ParquetSharp
CIPS-3D - 3D-aware GANs based on NeRF (arXiv).