Instant neural graphics primitives: lightning fast NeRF and more

Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Fast parallel CTC.

GPU Accelerated t-SNE for CUDA with Python bindings

GPU database engine

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …

Fuse multiple depth frames into a TSDF voxel volume.

Instant neural graphics primitives: lightning fast NeRF and more

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

NeRFshop: Interactive Editing of Neural Radiance Fields

PopSift is an implementation of the SIFT algorithm in CUDA.

NVIDIA-accelerated zero latency video compression library for interactive remoting applications

A simple GPU hash table implemented in CUDA using lock free techniques

This is a monocular dense mapping system corresponding to IROS 2018 "Quadtree-accelerated Real-time Monocular Dense Mapping"

PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression

GPU-accelerated triangle mesh processing

an implementation of parallel linear BVH (LBVH) on GPU

C++ Code to run waveglow inference in cuda

Code repository for the massively-parallel framework for maximum-likelihood fits, implemented in CUDA/OpenMP

GPU accelerated pre-filtered cubic b-spline interpolation using CUDA

GPU Fluid Simulation with Volumetric Rendering

Blazingly fast encoding for neural networks based on permutohedral lattices

A high-performance CUDA-based physics simulation sandbox for soft robotics and reinforcement learning.

A C++/CUDA library to efficiently compute neighborhood information on the GPU for 3D point clouds within a fixed radius.

GPU-based large scale Approx. Nearest Neighbor Search, accepted at CVPR 2016

GPU Recursive Filtering

Connected Component Labeling.

GPU implementation of LATCH descriptor & matcher.