Build 3D Gaussian Splatting from scratch with NVIDIA Warp in Python — CPU/GPU compatible, with a clean and minimalist design focused on learning modern graphics.

Python library for reading and writing image data

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

[NeurIPS 2024] The official implementation of HairFastGAN. A framework for virtual hairstyle fitting.

OpenVDB - Sparse volume data structure and tools

Machine Learning Systems

GPU Programming with C++ and CUDA, published by Packt

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

A C++ & Python viewer for 3D data like meshes and point clouds

Official project repository for the Setuptools build system

Vector class library, latest version

TinyXML2 is a simple, small, efficient, C++ XML parser that can be easily integrated into other programs.

HighFive - Header-only C++ HDF5 interface

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Release repo for our SLAM Handbook

A real-time CUDA-accelerated ray tracer built with OpenGL for interactive 3D rendering.

Cameras as Relative Positional Encoding

3D mathematical functions using NumPy

Complete solutions to the Programming Massively Parallel Processors Edition 4

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

RenderMe-360: Large Digital Asset Library and Benchmark Towards High-fidelity Head Avatars

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[ICCV - 2023] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

PyTorch code and models for the DINOv2 self-supervised learning method.

Schedule-Free Optimization in PyTorch

Create 3DGS heads from latent vectors

Modern OpenGL binding for Python

stb single-file public domain libraries for C/C++