Instant neural graphics primitives: lightning fast NeRF and more

Fast parallel CTC.

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

Efficient GPU kernels for block-sparse matrix multiplication and convolution

Fuse multiple depth frames into a TSDF voxel volume.

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

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

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

GPU-accelerated triangle mesh processing

Learning Deformable Tetrahedral Meshes for 3D Reconstruction (NeurIPS 2020)

A refactored codebase for Gaussian Splatting. Faster(3.5x)!! Modular!! Pure Python or CUDA Extension