1. Software
1.1. GPU
1.1.1. SiftGPU
1.2. Libraries
1.2.1. Image Processing
1.2.1.1. OpenCV
1.2.1.2. Intel IPP
1.3. Toolkits
1.3.1. ARToolkit
1.3.1.1. NYARToolkit
1.3.1.2. FLARToolkit
1.3.2. ARToolkitPlus
1.3.3. IN2AR
1.3.4. BazAR
1.4. Frameworks
1.4.1. Studierstube
1.4.2. Windage
1.5. Platforms
1.5.1. Adobe Flash
1.5.1.1. IN2AR
1.5.1.2. FLARToolkit
1.5.1.3. flare
1.5.2. Mobile
1.5.2.1. Android
1.5.2.2. iOS
1.6. Kinect based
1.7. Biometrics
1.7.1. Face
1.7.1.1. Detection
1.7.1.1.1. PAM
1.7.1.1.2. FaceL
1.7.1.1.3. fdlib
1.7.1.1.4. visage
1.7.1.1.5. Fu Jie Traker
1.7.1.2. Pose Estimation
1.7.1.2.1. on OpenCV
1.7.1.2.2. ehci
1.7.1.2.3. FaceAPI
1.7.1.3. gase pose estimation
1.7.2. Hand
1.8. Closed Software
1.8.1. Total Imerssion
1.8.2. Metaio
1.8.3. FaceAPI
2. Algorithms
2.1. Image Processing
2.1.1. Edge Detecting
2.1.2. Adaptive Thresholding
2.2. Tracking
2.2.1. Feature Tracking
2.2.1.1. Lucas-Kanade Optical Flow
2.2.1.1.1. [1994] Good Features to Track.pdf
2.2.1.1.2. [2004] Lucas-Kanade 20 Years On- A Unifying Framework.pdf
2.2.2. Edge Tracking
2.2.2.1. RAPiD
2.2.2.1.1. [2000] RAPiD- Real-time tracking of multiple articulated structures in multiple views.pdf
2.2.2.1.2. [2006] Full-3D Edge Tracking with a Particle Filter.pdf
2.2.3. Template Matching based Tracking
2.2.3.1. Lucas Kanade Algorithm
2.2.3.2. Iverse Compositional
2.2.3.3. ESM
2.2.4. Marker Tracking
2.2.4.1. Template markers
2.2.4.2. ID markers
2.2.4.3. Frame markers
2.2.4.4. Fiducial markers
2.2.5. Blob Tracking
2.2.6. Motion Tracking
2.2.6.1. Integral background substraction
2.3. Object Recognition
2.3.1. Feature based
2.3.1.1. Feature Extractor
2.3.1.1.1. Corner based
2.3.1.1.2. Region based
2.3.1.1.3. Point based (corner)
2.3.1.2. Descriptor
2.3.1.2.1. Distribution based
2.3.1.2.2. Shape Descriptor for MSER
2.3.1.2.3. Filter based
2.3.1.2.4. Textons
2.3.1.3. Feature Matching
2.3.1.3.1. KDTree
2.3.1.3.2. Spilltree
2.3.1.3.3. FLANNtree
2.3.1.4. Find Correspondence Image
2.3.1.4.1. Vocabulary tree
2.3.2. Training based
2.3.2.1. Classification based
2.3.2.1.1. Ferns
2.3.2.1.2. Oneway Descriptor
2.4. Pose Estimation
2.4.1. Plane
2.4.2. PnP
2.4.2.1. EPnP
2.4.3. P3A
2.5. Refinement
2.5.1. Robust Estimator
2.5.1.1. M-estimator
2.5.1.2. RANSAC
2.5.1.3. ProSAC
2.5.1.4. LMedS
2.5.2. Nmerical Optimisation
2.5.3. Estimation & Correction
2.5.3.1. Kalman Filter
2.5.3.2. Particle Filter
2.6. SLAM / PTAM
2.6.1. SLAM
2.6.1.1. [2003] Real-Time Simultaneous Localisation and Mapping with a Single Camera.pdf
2.6.1.2. [2007] MonoSLAM- Real-Time Single Camera SLAM.pdf
2.6.2. PTAM
2.6.2.1. [2007] Parallel Tracking and Mapping for Small AR Workspaces.pdf
2.6.2.2. [2009] Object Recognition and Localization while Tracking and Mapping.pdf
2.6.3. PTAMM
2.7. Reconstruction
2.7.1. Dense Matching
2.7.1.1. Wide Base Line Stereo Matching
2.7.2. Sparse Matching
2.7.2.1. Multi-view Reconstruction
2.7.2.2. Optimization
2.7.3. Rough Reconstruction
2.7.3.1. Visual Hull
2.8. Extreme Environment
2.8.1. Multiple objects
2.8.2. Mobile Devices
2.8.2.1. [2009] Robust feature matching in 2.3ms
2.8.2.2. [2008] Robust and Unobtrusive Marker Tracking on Mobile Phones
2.8.2.3. [2009] Multiple Target Detection and Tracking with Guaranteed Framerates on Mobile Phones
2.8.2.4. [2009] Parallel Tracking and Mapping on a Camera Phone
2.8.3. Illumination Change
2.8.3.1. [2007] Real-time Visual Tracking under Arbitrary Illumination Changes
2.8.3.2. [2008] 3D Pose Refinement from Reflections
2.8.4. Motion Blur
2.8.5. Unknown 3D Object
2.8.6. Deformable Object
2.8.7. Multiple Cameras
2.8.7.1. [2004] Fast Model Tracking with Multiple Cameras for Augmented Reality
2.8.7.2. [2006] Robust model-based tracking with multiple cameras for spatial applications
2.8.8. Large Viewpoint change
2.9. Biometrics
2.9.1. Face
2.9.1.1. Algorithms
2.9.2. Hand
3. Research centers
3.1. Directory
3.2. EPFL CVLab
3.2.1. Projects
3.2.1.1. BazAR A vision based fast detection library
3.2.1.2. POM Occupancy map estimation for people detection
3.2.1.3. EPnP Efficient Perspective-n-Point Camera Pose Estimation
3.2.1.4. DAISY A Fast Local Descriptor for Dense Matching
3.2.1.5. Efficient Large Scale Multi-View Stereo for Ultra High Resolution Image Sets
3.2.1.6. Ferns Planar Object Detection Demo
3.2.1.7. Emvisi2 A background subtraction algorithm, robust to sudden light changes
3.2.1.8. SLIC Superpixels
3.2.1.9. LDAHash Dynamic and Scalable Large Scale Image Reconstruction
3.2.1.10. BRIEF Binary Independent Elementary Features
3.2.1.11. Monocular 3D deformable surface reconstruction
3.3. TU Graz
3.3.1. Projects
3.3.1.1. Studerstube framework
3.3.1.2. ARToolkitPlus
3.4. Cambridge MI | CV group
3.5. Oxford Active Vision Lab
3.5.1. Projects
3.5.1.1. PTAM
3.5.2. Personalies
3.6. GIST
3.6.1. Projects
3.6.1.1. Windage
3.6.2. Personalies
3.6.2.1. Woonhyuk Baek
3.6.2.2. Woontack Woo
3.7. UCLA Vision Lab
4. Companies
4.1. Total Imerssion
4.1.1. Technologies
4.1.1.1. Marker based tracking
4.1.1.2. NFT based tracking
4.1.1.3. 6DOF Face tracking
4.1.2. Products
4.1.2.1. D'fusion
4.1.3. Cases
4.1.3.1. ...
4.2. Metaio
4.2.1. Technologies
4.2.1.1. Marker based tracking
4.2.1.2. NFT tracking
4.2.1.3. Object tracking
4.2.2. Products
4.2.2.1. Junaio platform
4.2.2.2. Unifeye
4.2.3. Cases
4.2.3.1. ...
4.3. Layar
4.3.1. Products
4.3.1.1. Layar platform
4.4. EligoVision
4.4.1. Technologies
4.4.1.1. Marker based tracking
4.4.2. Cases
4.4.2.1. XXL | AR Promo
4.4.2.2. Xaker | AR Promo
4.4.2.3. НегоциантЪ | AR demonstration
4.4.2.4. Poster one | AR web demo
4.4.2.5. AR installation
4.4.2.6. 11 cases for exhibition
4.4.2.7. 6 cases for science
4.4.2.8. 6 interactive cases
4.5. AR Door
4.5.1. works on
4.5.1.1. Total Imerssion platforms
4.5.2. cases
4.5.2.1. Tron| AR Promo
4.5.2.2. YESS | AR installation
4.5.2.3. Free-lance | AR installation
4.5.2.4. Espresso mania | AR Kiosk
4.5.2.5. Watch | Fittingroom demo
4.5.2.6. LG 3D TV | AR promo
4.5.2.7. Audi A1 | Mobile AR promo
4.5.2.8. ВАО Москва | Mobile AR navigation
4.5.2.9. Dom.ru | Mobile AR
4.5.2.10. eTarget |AR exhibition
4.6. Ailove
4.6.1. Technologies
4.6.1.1. Marker based tracking
4.6.1.2. NFT based tracking
4.6.1.3. Face tracking
4.6.1.4. Motion tracking
4.6.1.5. Blob tracking
4.6.2. Products
4.6.2.1. CV/AR Framework
4.6.3. Cases
4.6.3.1. Metroshka
4.6.3.2. TMED | AR Presentation
4.6.3.3. Bolshoi Theatre | presentation
4.6.3.4. Renault | Koleos AR promo
4.6.3.5. Winston | AR Kiosk
4.6.3.6. AXE | AR promo
4.6.3.7. SoniEricson | AR promo
4.6.3.8. Pepsi |AR promo
4.6.3.9. LG | AR promo
4.6.3.10. Grape | AR promo
4.6.3.11. ViralDay | AR promo
4.6.4. Prototypes
4.6.4.1. CocaCola | AR proto
4.6.4.2. RitterSport | AR proto
4.6.4.3. Renault | Koleos AR proto
4.6.4.4. Augmented Rabbit
4.6.4.5. Car control
4.6.4.6. Helicopter
4.6.5. also works with
4.6.5.1. Junaio platform
4.6.5.2. Layar platform
4.7. RedMadRobot
4.7.1. Technologies
4.7.1.1. Marker based tracking (ARToolkit)
4.7.2. Cases
4.7.2.1. Сытоедов | AR Kiosk
4.7.2.2. La redoute | Fittingroom
4.7.2.3. Grant's | AR promo
4.7.2.4. РОСНАНО | AR Exhibition
4.7.2.5. QUO | AR Kiosk
4.7.2.6. Chevrolet | AR promo kiosk
4.7.2.7. Kalyga | AR Exhibition
4.7.2.8. Русский пионер | AR promo
4.7.2.9. JV | AR quest
4.7.2.10. Sobranie | Ar promo stend
4.7.2.11. F5 | AR pages
4.7.3. Prototype
4.7.3.1. Molekula iz atomov proto
4.7.3.2. Watch | Fittingroom demo
4.8. 2Nova
4.8.1. Technologies
4.8.1.1. Marker, face based tracking only web / FLARtoolkit
4.8.2. Cases
4.8.2.1. Sony Ericsson | AR promo
4.8.2.2. Sony Alpha | AR web promo
4.8.2.3. Vogue | Virtual Fittingroom
4.8.2.4. Sony Ericsson | Webcam game
4.8.2.5. Kent | AR web promo
4.8.2.6. Sochi2014 | AR game
4.8.2.7. Abbott | AR audience game
4.8.2.8. Megafon | Webcam game
5. Hardware
5.1. Glasses
5.1.1. Vuzix
5.2. Cameras
5.2.1. 1394
5.2.2. USB
5.2.2.1. Logitech 910C
5.2.2.2. Logitech 905
5.2.2.3. Kinect