Welcome to ƒVDB!
fVDB is a Python library of data structures and algorithms for building high-performance and large-domain spatial applications using NanoVDB on the GPU in PyTorch. Applications of fVDB include 3D deep learning, computer graphics/vision, robotics, and scientific computing.
fVDB aims to be production ready with a focus on robustness, usability, and extensibility. It is designed to be easily integrated into existing pipelines and workflows, and to support a wide range of use cases and applications. To this end, fVDB has a minimal set of dependencies and is open source under the Apache 2.0 license as part of the The Academy Software Foundation’s OpenVDB project. Contributions and feedback from the community are welcome to fVDB’s GitHub repository.
Features
fVDB provides the following key features:
A sparse volumetric grid data structure optimized for GPU memory efficiency and performance.
A highly optimized Gaussian splat data structure for representing radiance fields on the GPU.
A jagged tensor data structure for efficient representation of sparse, non-uniform data on the GPU.
A suite of GPU-accelerated algorithms for volumetric data manipulation, ray tracing, and volume rendering.
A state of the art visualizer capable of streaming massive volumetric datasets to a web browser or Jupyter notebook.
Modular neural network components for building 3D deep learning models that scale to large input sizes.
Seamless integration with PyTorch for easy use in deep learning workflows.
The videos below show fVDB being used for large-scale 3D reconstruction, simulation, and interactive visualization.
fVDB being used to reconstruct radiance (25 million splats) fields and TSDF volumes (100 million voxels) from images and points
fVDB being used to process a sparse SDF on a grid with 181 million voxels. Visualized in a browser.
About fVDB
fVDB was first developed by the NVIDIA High-Fidelity Physics Research Group within the NVIDIA Spatial Intelligence Lab, and continues to be developed with the OpenVDB community to suit the growing needs for a robust framework for spatial intelligence research and applications.
fVDB Reality Capture Toolbox
In addition to the core fVDB library, we also provide the fVDB Reality Capture toolbox, which is a collection of tools and utilities for 3D reconstruction and scene understanding using fVDB. Analogous to how torchvision provides datasets, models, and transforms for computer vision tasks, fVDB Reality Capture provides datasets, models, and algorithms for 3D reconstruction from sensor data.
Documentation