- Home
- AI 3D Scanning Software
- Nerfstudio
Nerfstudio
What it is
Nerfstudio is a free, open-source project with modular components and an API for creating, training, and testing Neural Radiance Fields. Included methods are Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto, its Gaussian Splatting implementation. Command-line tools process data, train and evaluate models, render videos, view trained scenes, and export models. A web viewer shows training in real time, supports scene interaction, custom camera trajectories, and videos from trained models. Share URLs let others follow progress, but they are publicly accessible and can add latency. Documented capture workflows use COLMAP, Polycam, or Record3D to turn phone video into a 3D render. Installation is available through pip, source, or Docker. Docker requires NVIDIA drivers capable of CUDA 11.8, and the quickstart requires an NVIDIA video card with CUDA installed. Windows installation is described as less tested and more fragile, with Linux recommended when available. Nerfstudio launched in October 2022 and is developed by Berkeley students and community contributors.
For and against
For
- Includes several NeRF and splatting methods
- Web viewer shows training in real time
- Supports COLMAP, Polycam, and Record3D workflows
- Provides API and command-line tools
- Exports PLY, OBJ, PNG, and JPEG
Against
- Requires an NVIDIA CUDA-capable video card
- Windows installation is less tested
- Shared viewer links are public
- Docker requires CUDA 11.8-capable drivers
The verdict
Nerfstudio combines model methods, capture pipelines, training tools, and a live web viewer in an open-source package. Hardware and platform requirements are important considerations before setup.
Who it suits
Nerfstudio suits developers, researchers, and technical artists building NeRF or Gaussian Splatting workflows. It is aimed at users comfortable with command-line installation and NVIDIA CUDA hardware.
On the record
- Capture integrations
- The project describes a capture-to-render pipeline using Colmap, Polycam, or Record3D.github.com · read 30 Sep 2026
- Data workflows
- The project documents full pipeline support with COLMAP, Polycam, or Record3D for turning phone video into a 3D render.github.com · read 29 Sep 2026
- Development
- Nerfstudio launched as an open-source project by Berkeley students in October 2022 and is developed by Berkeley students and community contributors.docs.nerf.studio · read 30 Sep 2026
- GPU requirement
- The repository quickstart requires an NVIDIA video card with CUDA installed; it says the library was tested with CUDA 11.8.github.com · read 30 Sep 2026
- Included Gaussian splatting
- Splatfacto is Nerfstudio’s Gaussian Splatting implementation.docs.nerf.studio · read 30 Sep 2026
- Included methods
- Included methods are Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto.docs.nerf.studio · read 29 Sep 2026
- Installation
- The documentation provides installation instructions using pip, source code, Pixi, and Docker.docs.nerf.studio · read 30 Sep 2026
- License
- The project’s GitHub page identifies its license as Apache-2.0.github.com · read 30 Sep 2026
- Logging and debugging
- The project supports Tensorboard and Wandb logging interfaces, code profiling, and built-in debugging tools.github.com · read 30 Sep 2026
- Methods
- Included methods include Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto.docs.nerf.studio · read 30 Sep 2026
- Platform limits
- The documentation says Windows installation is less tested and more fragile, and recommends Linux when available.docs.nerf.studio · read 29 Sep 2026
- Platform support
- The installation guide says Nerfstudio on Windows is less tested and more fragile, and recommends Linux when available.docs.nerf.studio · read 30 Sep 2026
- Project
- The documentation describes Nerfstudio as an open-source project launched by Berkeley students in October 2022 and developed by Berkeley students and community contributors.docs.nerf.studio · read 29 Sep 2026
- Purpose
- Nerfstudio provides a modular API for creating, training, and testing Neural Radiance Fields (NeRFs).docs.nerf.studio · read 30 Sep 2026
- Remote viewing
- The viewer supports share URLs that let others view training progress, and the documentation says these links are publicly accessible and introduce latency.docs.nerf.studio · read 29 Sep 2026
- Support
- The project directs users with questions to its Discord and provides documentation, tutorials, and a feedback form.docs.nerf.studio · read 30 Sep 2026
- Training tools
- Its command line includes tools to process data, train and evaluate models, render videos, view trained NeRFs, and export models.docs.nerf.studio · read 29 Sep 2026
- Viewer
- Its web-based visualizer can show training in real time, let users interact with scenes, and render custom camera trajectories.github.com · read 30 Sep 2026
