The new Windows Terminal and the original Windows console host, all in the same place!

An open autonomous driving platform

ncnn is a high-performance neural network inference framework optimized for the mobile platform

LeetCode Problems' Solutions

Open3D: A Modern Library for 3D Data Processing

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

Repository for OpenCV's extra modules

Lightning fast C++/CUDA neural network framework

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

Deformable Convolutional Networks v2 with Pytorch

a Realistic and Rich 3D Environment

A plugin for GTAV that transforms it into a vision-based self-driving car research environment.

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Python bindings for COLMAP

DynaSLAM is a SLAM system robust in dynamic environments for monocular, stereo and RGB-D setups

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

PyTorch code for the "Deep Neural Networks with Box Convolutions" paper

TVM integration into PyTorch

A 100x faster SVD for PyTorch⚡️

Code release for "Canonical Surface Mapping via Geometric Cycle Consistency"

Source code for: Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds), accepted at ACCV 2018

SegStereo: Exploiting Semantic Information for Disparity Estimation

some operator used in mxnet!