CUDA accelerated rasterization of gaussian splatting

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"

tutorial for writing custom pytorch cpp+cuda kernel, applied on volume rendering (NeRF)

Pytorch package to compute Chamfer distance between point sets (pointclouds).

Differentiable Iso-Surface Extraction Package (DISO)

3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt. (ICCV 2025)

A modular differential gaussian rasterization library.

[ECCV'24] On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy

Improved 3DGS rasterizer.

OptiX version of Pete Shirley's "Ray Tracing in One Weekend" (Final Chapter example only)

Parallel Dual Marching Cubes for Intersection-free Mesh

CUDA Marching Cube & Dual Marching Cube for Sparse Voxel SDFs