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

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

Marching cubes implementation for PyTorch environment.

Lightning fast differentiable SSIM.

Fixed Radius Nearest Neighbor Search on GPU

A CUDA reimplementation of the line/plane odometry of LIO-SAM. A point cloud hash map (inspired by iVox of Faster-LIO) on GPU is used to accelerate 5-neighbour KNN search. Run on Jetson Orin NX 8GB.

Official code release for "Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency"

Optmized Fused-SSIM