harry7557558/spirula-studio
Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 1 day ago, with 26 contributors on GitHub.
Use Cases & Benefits
- Trains 3D Gaussian Splatting models from raw photo or video inputs to textured mesh outputs using Vulkan or CUDA acceleration.
- Offers cross-vendor GPU support with extreme VRAM efficiency, enabling training of 10 million SH3 Gaussians in just 8GB VRAM without external dependencies.
- Use for creating high-quality 3D reconstructions from 360° or fisheye camera datasets without needing undistortion or separate SfM tools.
- Use for rapid prototyping and training of 3D models on diverse hardware including NVIDIA, AMD, Intel, and Apple Silicon GPUs via Vulkan compute.
- Use for integrating 3D Gaussian Splatting pipelines into workflows requiring built-in AI masking, frame extraction from videos, and metric scale recovery.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
GPL 3.0
Copyleft: distributing software that includes it generally requires releasing your source under the same license.
Community files
- README: present
Watch-outs
- GPL-style copyleft: including it in distributed software generally requires releasing your source under the same license.
General guidance from repository metadata, not legal advice. How we score
From the README
Spirula Studio trains 3D Gaussian Splatting models – from raw photo/video to splat to textured mesh – in one self-contained binary. No Python/PyTorch, no separate COLMAP install. Runs on NVIDIA, AMD, Intel, and Apple GPUs via Vulkan, trains 10M full-SH Gaussians in 8 GB VRAM, and has native support for fisheye and 360° cameras.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+1,364 stars over 39 days across 4 snapshot days; best day +114 on Sep 24.
Forks
193+140
Open issues
79+43
Compared with peers in Computer Vision
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| mudler/LocalAI | 50.2K | +176 | 59 | 12 days ago |
| PaddlePaddle/PaddleOCR | 92.3K | — | 47 | 147 days ago |
| d2l-ai/d2l-en | 30.0K | — | 45 | — |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| SharpAI/DeepCamera | 3.1K | — | 31 | 227 days ago |
| harry7557558/spirula-studio | 2.1K | — | 55 | 1 day ago |
| Category median | 30.0K | — | 45 | — |
Discover Repositories
Search across tracked repositories by name or description