Nerfstudio: A Modular Framework for Neural Radiance Field Development

By Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, J. Austin, Kamyar Salahi and 3 more. International Conference on Computer Graphics and Interactive Techniques, 2023

995 citations recorded by the source corpus.

Neural Radiance Fields (NeRF) are a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more. In order to streamline the development and deployment of NeRF research, we propose a modular PyTorch framework, Nerfstudio. Our framework includes plug-and-play components for implementing NeRF-based methods, which make it easy for researchers and practitioners to incorporate NeRF into their projects. Additionally, the modular design enables support for extensive real-time visualization tools, streamlined pipelines for importing captured in-the-wild data, and tools for exporting to video, point cloud and mesh representations. The modularity of Nerfstudio enables the development of Nerfacto, our method that combines components from recent papers to achieve a balance between speed and quality, while also remaining flexible to future modifications. To promote community-driven development, all associated code and data are made publicly available with open-source licensing.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d293299a18e1daa706ce603abce02b9df8f0ca7a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, positive): “We compare G EN 3C to two representative scene reconstruction methods, Nerfacto [50] and 3DGS [25].”
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (2023, methodology): “As the underlying NeRF implementation, we use the ‘nerfacto’ model from NeRFStudio [41].”
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision (2023, neutral): “Ner-facto [27] merges elements from previous NeRF methods to balance speed and quality.”
NeRF: Representing scenes as neural radiance ﬁelds for view synthesis (neutral): “9 Given NeRF’s popularity, a number of software frameworks have been developed; one open source example is NeRFStudio [ 68 ].”
LERF: Language Embedded Radiance Fields (2023, methodology): “We implement LERF in Nerfstudio [35], on top of the Nerfacto method.”
ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes (2023, methodology): “For both experiments, we show re-sults of NeRF [27] and its state-of-the-art variants [29, 5, 41] on the validation scenes.”