ZephirFXEC / VQVDB
OpenVDB Fog Volume Compression using VQ-VAE Neural Network
Why this job: works in the areas we cover, but does not say which job it does
What it does
VQVDB is a deep learning–powered compressor for volumetric data stored in OpenVDB. It uses Vector Quantized Variational Autoencoders (VQ-VAE) to learn a compact latent space and achieves up to 32× compression of float voxel grids, nearly lossless at the visual level.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 5 months ago
- Stars
- 117
- +9 this week
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- None listed
- No release files
- Latest version
- v0.0.7-alpha
- Released 15 months ago
- Built with
- C++
- 99% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 82% closed
- 2 still open
- Pull requests
- 11 merged
- 2 waiting
- Releases
- 7
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| BobMcDear / attorch | 607 | 3 months ago | MIT | No downloads |
| openmm / NNPOps | 101 | 9 months ago | Custom | No downloads |
More: languages, topics and project record
Languages
- C++ 99%
- Jupyter Notebook 1%
- Python <1%
- CMake <1%
Topics
- cuda
- machine-learning
- openvdb
- vq-vae
Project record
- JobOther AI tools
- StatusListed
- Commits112
- Forks3
- Watching1
- Stars in 28 days+10
- CreatedJun 2, 2025
- First seen by usNov 7, 2026
- CheckedNov 12, 2026