harry7557558/spirula-studio

Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.

What it solves

Spirula Studio simplifies the creation of 3D Gaussian Splatting models, which are high-fidelity 3D representations of real-world scenes. It eliminates the need for complex Python environments, PyTorch dependencies, or external tools like COLMAP by bundling the entire pipeline—from raw photo/video input to final textured mesh—into a single, easy-to-use binary.

How it works

The software uses Vulkan compute to ensure cross-vendor compatibility, allowing it to run on NVIDIA, AMD, Intel, and Apple Silicon GPUs. It integrates several advanced techniques, including MCMC (Markov Chain Monte Carlo) for optimized point distribution, AI-based masking for background removal, and a built-in Structure-from-Motion (SfM) module to calculate camera positions and scene geometry from your images or videos.

Who it’s for

It is designed for 3D artists, researchers, and hobbyists who want to generate high-quality 3D assets from photos or videos without managing complex software dependencies or high-end server-side AI infrastructure.

Highlights

  • Cross-platform support for Windows, Linux, and macOS via Vulkan.
  • Memory-efficient training, capable of handling 10 million Gaussians within 8GB of VRAM.
  • Native support for 360° and fisheye cameras, removing the need for manual undistortion.
  • Built-in AI masking and rapid frame extraction from video files.
  • Includes tools for editing, meshing, and exporting 3D models and renders.

Related

  • Dispatch
    Introduction to 3D Gaussian Splatting

    3D Gaussian Splatting is a rasterization technique that enables real-time rendering of photorealistic 3D scenes learned from a small set of images.

  • Project
    WebODM/OpenSplat

    OpenSplat is a C++ implementation of 3‑D Gaussian splatting that converts COLMAP/OpenSfM/ODX/nerfstudio data into compact Gaussian‑based scene files. It supports CUDA, ROCm (HIP), Apple Metal, and CPU‑only builds, offers Docker images, and provides a simple CLI for training, resuming, masking, and exporting to .ply/.splat/.spz/.rad formats.

  • Project
    ooolabdev/ooosplat

    OOOSplat is a local desktop application that converts ordinary or panoramic video and image sequences into 3D Gaussian Splatting models with one click, handling frame extraction, camera reconstruction, and training entirely on your own CPU/GPU. It then lets you preview, edit, and export the result in multiple formats, all without uploading your footage to the cloud.

  • Project
    ArthurBrussee/brush

    A cross-platform 3D reconstruction engine using Gaussian splatting that runs on WebGPU and the Burn framework to support macOS, Windows, Linux, Android, and browsers.

  • Project
    MrNeRF/LichtFeld-Studio

    A modular workstation for 3D Gaussian Splatting that integrates training, real-time visualization, editing, and automation into a single native application.