Nerfstudio
nerf.studio
- Free plan
- Windows
- Linux
- Web
- API
- Self-hosted
What Nerfstudio is
Nerfstudio is a free, open-source project with an API for creating, training, and testing Neural Radiance Fields through modular components. 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. The web viewer displays training in real time, supports scene interaction, renders custom camera trajectories, and creates videos from trained models. Share URLs let others view progress, but the documentation says they are public and can add latency. 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. Logging, profiling, and debugging support includes Tensorboard and Wandb interfaces. Windows installation is described as less tested and more fragile than Linux.
Who it suits
Nerfstudio suits developers, researchers, and creators building NeRF or Gaussian Splatting workflows with self-managed infrastructure. It is relevant when Linux, NVIDIA CUDA hardware, and command-line tooling are available.
Good to know, and what to watch
- Open-source API and modular components
- Several NeRF and splatting methods included
- Real-time web training viewer
- COLMAP, Polycam, and Record3D workflows
- Pip, source, and Docker installation
- Windows installation is less tested and fragile
- NVIDIA CUDA hardware is required
- Shared viewer links are public and can add latency
- No measurement tools
The verdict
Nerfstudio offers an open toolkit spanning capture, training, viewing, evaluation, and export. Hardware requirements and the less-tested Windows path should shape deployment decisions.
What the maker publishes
- Capture integrations
- The project describes a capture-to-render pipeline using Colmap, Polycam, or Record3D. source
- Data workflows
- The project documents full pipeline support with COLMAP, Polycam, or Record3D for turning phone video into a 3D render. source
- Development
- Nerfstudio launched as an open-source project by Berkeley students in October 2022 and is developed by Berkeley students and community contributors. source
- Founded
- 2022 source
- GPU requirement
- The repository quickstart requires an NVIDIA video card with CUDA installed; it says the library was tested with CUDA 11.8. source
- Included Gaussian splatting
- Splatfacto is Nerfstudio’s Gaussian Splatting implementation. source
- Included methods
- Included methods are Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto. source
- Installation
- The documentation provides pip, source, and Docker installation options; Docker requires NVIDIA GPU drivers capable of CUDA 11.8. source
- Installation
- The documentation provides installation instructions using pip, source code, Pixi, and Docker. source
- License
- The project’s GitHub page identifies its license as Apache-2.0. source
- Logging and debugging
- The project describes support for Tensorboard and Wandb logging interfaces, code profiling, and built-in debugging tools. source
- Logging and debugging
- The project supports Tensorboard and Wandb logging interfaces, code profiling, and built-in debugging tools. source
- Methods
- Included methods include Nerfacto, Instant-NGP, NeRF, Mip-NeRF, TensoRF, and Splatfacto. source
- Platform limits
- The documentation says Windows installation is less tested and more fragile, and recommends Linux when available. source
- Platform support
- The installation guide says Nerfstudio on Windows is less tested and more fragile, and recommends Linux when available. source
- 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. source
- Purpose
- Nerfstudio provides an API for creating, training, and testing NeRFs through modular components. source
- Purpose
- Nerfstudio provides a modular API for creating, training, and testing Neural Radiance Fields (NeRFs). source
- 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. source
- Support
- The project directs users with questions to its Discord community and provides tutorials, documentation, and a feedback form. source
- Support
- The project directs users with questions to its Discord and provides documentation, tutorials, and a feedback form. source
- Training tools
- Its command line includes tools to process data, train and evaluate models, render videos, view trained NeRFs, and export models. source
- Viewer
- Its web-based visualizer can show training in real time, let users interact with scenes, and render custom camera trajectories. source
- Viewer integrations
- The web viewer is built using Viser and ThreeJS and packaged as a ReactJS application that connects to a server through a websocket. source
Checked against the maker's pages on 30 Sept 2026.