4 projects
fussim
Optimized CUDA implementation of differentiable SSIM for PyTorch
gsply
Ultra-fast Gaussian Splatting PLY I/O library - pure Python with NumPy and Numba. Features 11x faster GPU transfers and automatic format state tracking for seamless conversions.
bae-kai
PyTorch implementation of Bundle Adjustment in the Eager-mode
gsmod
Ultra-fast CPU processing for 3D Gaussian Splatting (color, transform, filter, opacity)
