Repository Index

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

• human-pose-estimation
• realtime
• caffe
• human-behavior-understanding

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

• deep-learning
• image-matching
• pose-estimation
• transformers

An advanced, unified platform for code quality, architectural metrics, and Agile analytics. Features Python AST parsing, Java static analysis (code smells), and interactive project health dashboards built with Streamlit.

• agile
• code-analysis
• dashboard
• data-visualization

[ICCV 2019] Monocular depth estimation from a single image

• depth-estimation
• neural-network
• deep-learning
• self-supervision

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

• human-pose-estimation
• deep-learning
• coco-keypoints-detection
• mpii-dataset

A curated list of papers & resources linked to 3D reconstruction from images.

• computer-vision
• 3d-reconstruction
• motion-estimation
• awesome-list

Visual localization made easy with hloc

• deep-learning
• visual-localization
• feature-matching
• image-retrieval

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

• deep-learning
• feature-matching
• pose-estimation
• graph-neural-networks

A curated list of action recognition and related area resources

• awesome-list
• awesome
• action-recognition
• action-classification

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

• 3d-reconstruction
• ai
• calibration
• depth-completion

Python Kalman filtering and optimal estimation library. Implements Kalman filter, particle filter, Extended Kalman filter, Unscented Kalman filter, g-h (alpha-beta), least squares, H Infinity, smoothers, and more. Has companion book 'Kalman and Bayesian Filters in Python'.

SpeedTest by OpenSpeedTest™ is a Free and Open-Source HTML5 Network Performance Estimation Tool Written in Vanilla Javascript and only uses built-in Web APIs like XMLHttpRequest (XHR), HTML, CSS, JS, & SVG. No Third-Party frameworks or libraries are Required. Started in 2011 and moved to OpenSpeedTest.com dedicated Project/Domain Name in 2013.

• html5
• xhr2
• css
• svg

GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.

• estimation
• perception
• robotics
• sensorfusion

A procedural Blender pipeline for photorealistic training image generation

• blender-pipeline
• segmentation
• depth-images
• camera-positions

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

• 3d-reconstruction
• depth-prediction
• feature-matching
• global-features

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

A curated list of resources for Image and Video Deblurring

• image-deblurring
• video-deblurring
• image-deconvolution
• stereo-deblurring

POT : Python Optimal Transport

• optimal-transport
• numerical-optimization
• machine-learning
• emd

CasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained C-code generation and interfaces state-of-the-art codes such as SUNDIALS, IPOPT etc. It can be used from C++, Python, Matlab/Octave, Julia or Javascript

• optimization
• nonlinear
• derivatives
• code-generation

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

• deep-learning
• depth-prediction
• visual-odometry
• self-supervised-learning

robot_localization is a package of nonlinear state estimation nodes. The package was developed by Charles River Analytics, Inc. Please ask questions on answers.ros.org.

Natural Gradient Boosting for Probabilistic Prediction

• machine-learning
• gradient-boosting
• natural-gradients
• uncertainty-estimation

Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.

• convolutional-neural-networks
• motion-tracking
• color-detection
• face-detection