Nerfstudio: A Modular Framework for Neural Radiance Field Development

Abstract

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 at https://nerf.studio.

Project page at https://nerf.studio

References in corpus (1)

• NeAT: Neural Adaptive Tomography

Cited by in corpus (26)

• MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
• SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection
• Reviewing Intelligent Cinematography: AI research for camera-based video production
• Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation
• GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
• DifFRelight: Diffusion-Based Facial Performance Relighting
• Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
• ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields
• Crowd-Sourced NeRF: Collecting Data from Production Vehicles for 3D Street View Reconstruction
• Osprey: Multi-Session Autonomous Aerial Mapping with LiDAR-based SLAM and Next Best View Planning
• Geometric implicit neural representations for signed distance functions
• Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
• Dynamic NeRFs for Soccer Scenes
• Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets
• Neural Light Spheres for Implicit Image Stitching and View Synthesis
• MATTERIX: toward a digital twin for robotics-assisted chemistry laboratory automation
• EasyVolcap: Accelerating Neural Volumetric Video Research
• AquaNeRF: Neural Radiance Fields in Underwater Media with Distractor Removal
• InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
• Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison
• Splat and Replace: 3D Reconstruction with Repetitive Elements
• P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments
• HAL-NeRF: High Accuracy Localization Leveraging Neural Radiance Fields
• Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate Regression
• Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects
• A Gaussian Parameterization for Direct Atomic Structure Identification in Electron Tomography