Watch the SIGGRAPH announcement video and demo reel showcasing how NeuralVDB revolutionizes complex volumetric simulations across industries with an up to 100x memory footprint reduction.

NeuralVDB is a large-scale volume representation with AI-enabled data compression technology. It offers significant efficiency improvements over OpenVDB, the industry-standard library for simulating and rendering sparse volumetric data such as water, fire, smoke and clouds.

Interested in testing out the NeuralVDB SDK? Please join our Early Access Program and share more about your use case. Please register or log in using your company email credentials to help us evaluate and grant access. Thanks for your patience as we expand this program.

Join now

Explore the benefits of NeuralVDB

Multi-Sector Innovation

Sparse volumetric data can be found across a larger body of work than ever before. Medical, industrial, robotics, graphics, and other fields demand high-resolution real-time simulations at unprecedented magnitudes but corresponding memory demands can conflict with hardware constraints. NerualVDB solves this issue by offering incredibly efficient memory representations at the cost of small to negligible quality loss, allowing for volumetric applications at extreme resolutions.

Built on OpenVDB

OpenVDB is the industry standard library for simulating and rendering dynamic volumes. Expanding on this foundation, NVIDIA introduced GPU-accelerated processing with NanoVDB for dramatically improved performance. Now, NeuralVDB takes all the features and optimizations of its predecessors and introduces a structure of compact neural representations that reduces memory footprints up to 100x. NeuralVDB is the next evolution of the VDB library.

Seamless Integration

VDB data is encoded into NeuralVDB representations through a compressor that prioritizes preserving information and temporal coherency between frames. NeuralVDB representations can then be readily decoded back into standard VDB volumes. In essence, NeuralVDB was built to be compatible with preexisting VDB pipelines. This ensures that adopting NeuralVDB into production workflows will be as seamless as possible.

Stay up to date on NVIDIA NeuralVDB news

Bringing AI and GPU Optimization to Award-Winning OpenVDB

Upping the Standard: NVIDIA Introduces NeuralVDB, Bringing AI and GPU Optimization to Award-Winning OpenVDB

Read the official announcement for NeuralVDB and how it revolutionizes volumetric data visualization across uses in special effects, medical research, and other industries.

Read Blog Post
NeuralVDB Hierarchical Networks

NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

Explore the breakthrough research paper that introduces NeuralVDB, detailing how it applies machine learning innovations to VDB volume storage for maximized visual fidelity and scale.

Read Research Paper

Interested in testing out the NeuralVDB SDK?

Join now