fmannan

diffrend

Differentiable Renderer

argoverse-api

Official GitHub repository for Argoverse dataset

autoware

Autoware - the world's leading open-source software project for autonomous driving

boomerang

Boomerang Decompiler - Fighting the code-rot :)

caffe

Caffe: a fast open framework for deep learning.

render_server

OpenGL based Render Server

carla

Open-source simulator for autonomous driving research.

colmap

COLMAP - Structure-from-Motion and Multi-View Stereo

CUDA-PointPillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

cvat

Powerful and efficient Computer Vision Annotation Tool (CVAT)

cycada_release

Code to accompany ICML 2018 paper

darknet

Convolutional Neural Networks

DeepV2D

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

dso

Direct Sparse Odometry

high-res-stereo

Hierarchical Deep Stereo Matching on High Resolution Images, CVPR 2019.

nuscenes-devkit

The devkit of the nuScenes dataset.

openMVG

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

OpenSfM

Open source Structure from Motion pipeline

ORB_SLAM3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

pix2shape

Modelling 3D structure from Images

qd-3dt

Official implementation of Monocular Quasi-Dense 3D Object Tracking, TPAMI 2022

RAFT

RAFT-Stereo

redtail

NVidia Redtail project with ArduPilot Support for Jetpack 4.2.x

scalabel

Quantify computer vision performance in human terms

ScaledYOLOv4

Scaled-YOLOv4: Scaling Cross Stage Partial Network

synsin

View synthesis for the public.

torch2trt

An easy to use PyTorch to TensorRT converter

Vitis-AI

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.