Why This Matters
The latest release of GaussianSplatting.jl 2.0 significantly enhances the capabilities and usability of Gaussian splatting in Julia, supporting multiple GPU backends, multithreaded UI for responsiveness, and advanced strategies like MCMC for better scene control. These improvements streamline workflows for developers and researchers, making high-quality 3D rendering and reconstruction more accessible and efficient across various hardware platforms.
Key Takeaways
- Supports multiple GPU backends (AMD, NVIDIA, MacBook) via KernelAbstractions.jl.
- Introduces multithreaded UI to keep the application responsive during intensive tasks.
- Adds advanced features like MCMC densification and depth supervision for improved scene quality.
Better Gaussian Splatting in Julia
GaussianSplatting.jl 2.0 release brings notable quality of life improvements and new capabilities.
Same code, multiple GPU backends
Written entirely in Julia it supports following GPU backends:
AMD GPU (AMDGPU.jl)
NVIDIA GPU (CUDA.jl)
MacBook GPU(Metal.jl)
This is achieved with KernelAbstractions.jl that allows writing a single kernel that get's compiled to a specific target.
Multithreaded UI
To avoid freezing the app during heavy work (such as JIT compilation of GPU kernels, dataset loading, etc.) the app is now split into two threads:
... continue reading
GoKawiil