机器视觉
Awesome Computer Vision: 
¶
精选的计算机视觉资源列表，灵感来自 awesome-php.
如需计算机视觉领域的人物名单及其学术谱系，请访问 here
Contributing¶
请随时寄给我 pull requests 或发送电子邮件 (jbhuang@vt.edu) 添加链接.
Awesome Lists¶
- Awesome Machine Learning
- Awesome Deep Vision
- Awesome Domain Adaptation
- Awesome Object Detection
- Awesome 3D Machine Learning
- Awesome Action Recognition
- Awesome Scene Understanding
- Awesome Adversarial Machine Learning
- Awesome Adversarial Deep Learning
- Awesome Face
- Awesome Face Recognition
- Awesome Human Pose Estimation
- Awesome medical imaging
- Awesome Images
- Awesome Graphics
- Awesome Neural Radiance Fields
- Awesome Implicit Neural Representations
- Awesome Neural Rendering
- Awesome Public Datasets
- Awesome Dataset Tools
- Awesome Robotics Datasets
- Awesome Mobile Machine Learning
- Awesome Explainable AI
- Awesome Fairness in AI
- Awesome Machine Learning Interpretability
- Awesome Production Machine Learning
- Awesome Video Text Retrieval
- Awesome Image-to-Image Translation
- Awesome Image Inpainting
- Awesome Deep HDR
- Awesome Video Generation
- Awesome GAN applications
- Awesome Generative Modeling
- Awesome Image Classification
- Awesome Deep Learning
- Awesome Machine Learning in Biomedical(Healthcare) Imaging
- Awesome Deep Learning for Tracking and Detection
- Awesome Human Pose Estimation
- Awesome Deep Learning for Video Analysis
- Awesome Vision + Language
- Awesome Robotics
- Awesome Visual Transformer
- Awesome Embodied Vision
- Awesome Anomaly Detection
- Awesome Makeup Transfer
- Awesome Learning with Label Noise
- Awesome Deblurring
- Awsome Deep Geometry Learning
- Awesome Image Distortion Correction
- Awesome Neuron Segmentation in EM Images
- Awsome Delineation
- Awesome ImageHarmonization
- Awsome GAN Training
- Awesome Document Understanding
Books¶
Computer Vision¶
- Computer Vision: Models, Learning, and Inference - Simon J.D. Prince 2012
- Computer Vision: Theory and Application - 里克·塞利斯基 2010
- Computer Vision: A Modern Approach (2nd edition) - 大卫·福赛斯和让·庞塞 2011
- Multiple View Geometry in Computer Vision - 理查德哈特利和安德鲁齐瑟曼 2004
- Computer Vision - 琳达·G·夏皮罗 2001
- Vision Science: Photons to Phenomenology - 斯蒂芬·E·帕尔默 1999
- Visual Object Recognition synthesis lecture - 克里斯汀格劳曼和巴斯蒂安雷贝 2011
- Computer Vision for Visual Effects - 理查德·拉德克 (Richard J. Radke)，2012 年
- High dynamic range imaging: acquisition, display, and image-based lighting - Reinhard, E., Heidrich, W., Debevec, P., Pattanaik, S., Ward, G., Myszkowski, K 2010
- Numerical Algorithms: Methods for Computer Vision, Machine Learning, and Graphics - 贾斯汀所罗门 2015
- Image Processing and Analysis - 斯坦·伯奇菲尔德 2018
- Computer Vision, From 3D Reconstruction to Recognition 西尔维奥·萨瓦雷塞 2018
OpenCV Programming¶
- Learning OpenCV: Computer Vision with the OpenCV Library - 加里布拉德斯基和阿德里安凯勒
- Practical Python and OpenCV - 阿德里安·罗斯布鲁克
- OpenCV Essentials - Oscar Deniz Suarez、Mª del Milagro Fernandez Carrobles、Noelia Vallez Enano、Gloria Bueno Garcia、Ismael Serrano Gracia
Machine Learning¶
- Pattern Recognition and Machine Learning - 克里斯托弗·M·毕晓普 2007
- Neural Networks for Pattern Recognition - Christopher M. Bishop 1995
- Probabilistic Graphical Models: Principles and Techniques - 达芙妮·科勒和尼尔·弗里德曼 2009
- Pattern Classification - Peter E. Hart、David G. Stork 和 Richard O. Duda 2000
- Machine Learning - 汤姆米切尔 1997
- Gaussian processes for machine learning - Carl Edward Rasmussen 和 Christopher KI Williams 2005
- Learning From Data- Yaser S. Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin 2012
- Neural Networks and Deep Learning - 迈克尔·尼尔森 2014
- Bayesian Reasoning and Machine Learning - David Barber，剑桥大学出版社，2012 年
Fundamentals¶
- Linear Algebra and Its Applications - 吉尔伯特斯特朗 1995
Courses¶
Computer Vision¶
- EENG 512 / CSCI 512 - Computer Vision - William Hoff（科罗拉多矿业学院）
- Visual Object and Activity Recognition - Alexei A. Efros 和 Trevor Darrell（加州大学伯克利分校）
- Computer Vision - Steve Seitz（华盛顿大学）
- 视觉识别 Spring 2016, Fall 2016 - 克里斯汀·格劳曼 (UT Austin)
- Language and Vision - Tamara Berg（北卡罗来纳大学教堂山分校）
- Convolutional Neural Networks for Visual Recognition - Fei-Fei Li and Andrej Karpathy (Stanford University)
- Computer Vision - 罗伯·弗格斯（纽约大学）
- Computer Vision - 德里克·霍伊姆 (UIUC)
- Computer Vision: Foundations and Applications - Kalanit Grill-Spector 和 Fei-Fei Li（斯坦福大学）
- High-Level Vision: Behaviors, Neurons and Computational Models - Fei-Fei Li (Stanford University)
- Advances in Computer Vision -Antonio Torralba 和 Bill Freeman（麻省理工学院）
- Computer Vision - Bastian Leibe（亚琛工业大学）
- Computer Vision 2 - Bastian Leibe（亚琛工业大学）
- Computer Vision 帕斯卡公式 (EPFL)：
- Computer Vision 1 Carsten Rother（德累斯顿工业大学）：
- Computer Vision 2 Carsten Rother（德累斯顿工业大学）：
- Multiple View Geometry Daniel Cremers（慕尼黑工业大学）：
Computational Photography¶
- Image Manipulation and Computational Photography - Alexei A. Efros（加州大学伯克利分校）
- Computational Photography - Alexei A. Efros (CMU)
- Computational Photography - 德里克·霍伊姆 (UIUC)
- Computational Photography - 詹姆斯·海斯（布朗大学）
- Digital & Computational Photography - 弗雷多杜兰德（麻省理工学院）
- Computational Camera and Photography - Ramesh Raskar（麻省理工学院媒体实验室）
- Computational Photography - Irfan Essa（佐治亚理工学院）
- Courses in Graphics - 斯坦福大学
- Computational Photography - 罗伯·弗格斯（纽约大学）
- Introduction to Visual Computing - Kyros Kutulakos（多伦多大学）
- Computational Photography - Kyros Kutulakos（多伦多大学）
- Computer Vision for Visual Effects - Rich Radke（伦斯勒理工学院）
- Introduction to Image Processing - Rich Radke（伦斯勒理工学院）
Machine Learning and Statistical Learning¶
- Machine Learning - Andrew Ng（斯坦福大学）
- Learning from Data - Yasser S. Abu-Mostafa（加州理工学院）
- Statistical Learning - Trevor Hastie 和 Rob Tibshirani（斯坦福大学）
- Statistical Learning Theory and Applications - Tomaso Poggio、Lorenzo Rosasco、Carlo Ciliberto、Charlie Frogner、Georgios Evangelopoulos、Ben Deen（麻省理工学院）
- Statistical Learning - Genevera Allen（莱斯大学）
- Practical Machine Learning - 迈克尔乔丹（加州大学伯克利分校）
- Course on Information Theory, Pattern Recognition, and Neural Networks - David MacKay（剑桥大学）
- Methods for Applied Statistics: Unsupervised Learning - 莱斯特麦基（斯坦福大学）
- Machine Learning - Andrew Zisserman（牛津大学）
- Intro to Machine Learning - Sebastian Thrun（斯坦福大学）
- Machine Learning - Charles Isbell、Michael Littman（佐治亚理工学院）
- (Convolutional) Neural Networks for Visual Recognition - Fei-Fei Li、Andrej Karphaty、Justin Johnson（斯坦福大学）
- Machine Learning for Computer Vision - Rudolph Triebel（慕尼黑工业大学）
Optimization¶
- Convex Optimization I - Stephen Boyd（斯坦福大学）
- Convex Optimization II - Stephen Boyd（斯坦福大学）
- Convex Optimization - Stephen Boyd（斯坦福大学）
- Optimization at MIT - （和）
- Convex Optimization - 瑞安·蒂布希拉尼 (CMU)
Papers¶
Conference papers on the web¶
- CVPapers - 网络上的计算机视觉论文
- SIGGRAPH Paper on the web - 网络上的图形文件
- NIPS Proceedings - 网络上的 NIPS 论文
- Computer Vision Foundation open access
- Annotated Computer Vision Bibliography - 基思普莱斯（南加州大学）
- Calendar of Computer Image Analysis, Computer Vision Conferences -（南加州大学）
Survey Papers¶
- Visionbib Survey Paper List
- Foundations and Trends® in Computer Graphics and Vision
- Computer Vision: A Reference Guide
##预训练的计算机视觉模型 * List of Computer Vision models 这些模型是在自定义对象上训练
Tutorials and talks¶
Computer Vision¶
- Computer Vision Talks - 关于计算机视觉的讲座、主题演讲、小组讨论
- The Three R's of Computer Vision - Jitendra Malik（加州大学伯克利分校）2013
- Applications to Machine Vision - Andrew Blake（微软研究院）2008
- The Future of Image Search - Jitendra Malik（加州大学伯克利分校）2008
- Should I do a PhD in Computer Vision? - Fatih Porikli（澳大利亚国立大学）
- Graduate Summer School 2013: Computer Vision - IPAM, 2013
Recent Conference Talks¶
- CVPR 2015 - Jun 2015
- ECCV 2014 - 2014 年 9 月
- CVPR 2014 - Jun 2014
- ICCV 2013 - 2013 年 12 月
- ICML 2013 - 2013 年 7 月
- CVPR 2013 - Jun 2013
- ECCV 2012 - 2012 年 10 月
- ICML 2012 - Jun 2012
- CVPR 2012 - Jun 2012
3D Computer Vision¶
- 3D Computer Vision: Past, Present, and Future - Steve Seitz（华盛顿大学）2011
- Reconstructing the World from Photos on the Internet - Steve Seitz（华盛顿大学）2013
Internet Vision¶
- The Distributed Camera — Noah Snavely（康奈尔大学）2011
- Planet-Scale Visual Understanding — Noah Snavely（康奈尔大学）2014
- A Trillion Photos - Steve Seitz（华盛顿大学）2013
Computational Photography¶
- Reflections on Image-Based Modeling and Rendering - Richard Szeliski（微软研究院）2013
- Photographing Events over Time - 威廉·弗里曼 (麻省理工学院) 2011
- Old and New algorithm for Blind Deconvolution - Yair Weiss（耶路撒冷希伯来大学）2011
- A Tour of Modern "Image Processing" - Peyman Milanfar（加州大学圣克鲁兹分校/谷歌）2010
- Topics in image and video processing Andrew Blake（微软研究院）2007
- Computational Photography - 威廉·弗里曼 (麻省理工学院) 2012
- Revealing the Invisible - Fredo Durand (麻省理工学院) 2012
- Overview of Computer Vision and Visual Effects - Rich Radke（伦斯勒理工学院）2014
Learning and Vision¶
- Where machine vision needs help from machine learning - 威廉·弗里曼 (麻省理工学院) 2011
- Learning in Computer Vision - 西蒙·卢西 (CMU) 2008
- Learning and Inference in Low-Level Vision - Yair Weiss（耶路撒冷希伯来大学）2009
Object Recognition¶
- Object Recognition - 拉里齐特尼克（微软研究院）
- Generative Models for Visual Objects and Object Recognition via Bayesian Inference - Fei-Fei Li (Stanford University)
Graphical Models¶
- Graphical Models for Computer Vision - Pedro Felzenszwalb（布朗大学）2012
- Graphical Models - Zoubin Ghahramani（剑桥大学）2009
- Machine Learning, Probability and Graphical Models - Sam Roweis（纽约大学）2006
- Graphical Models and Applications - Yair Weiss（耶路撒冷希伯来大学）2009
Machine Learning¶
- A Gentle Tutorial of the EM Algorithm - Jeff A. Bilmes（加州大学伯克利分校）1998
- Introduction To Bayesian Inference - Christopher Bishop（微软研究院）2009
- Support Vector Machines - Chih-Jen Lin（国立台湾大学）2006
- Bayesian or Frequentist, Which Are You? - Michael I. Jordan（加州大学伯克利分校）
Optimization¶
- Optimization Algorithms in Machine Learning - Stephen J. Wright（威斯康星大学麦迪逊分校）
- Convex Optimization - Lieven Vandenberghe（加州大学洛杉矶分校）
- Continuous Optimization in Computer Vision - Andrew Fitzgibbon（微软研究院）
- Beyond stochastic gradient descent for large-scale machine learning -弗朗西斯·巴赫 (INRIA)
- Variational Methods for Computer Vision - Daniel Cremers（慕尼黑工业大学）（lecture 18 missing from playlist)
Deep Learning¶
- A tutorial on Deep Learning - Geoffrey E. Hinton（多伦多大学）
- Deep Learning - Ruslan Salakhutdinov（多伦多大学）
- Scaling up Deep Learning - Joshua Bengio（蒙特利尔大学）
- ImageNet Classification with Deep Convolutional Neural Networks - Alex Krizhevsky（多伦多大学）
- The Unreasonable Effectivness Of Deep Learning Yann LeCun（纽约大学/Facebook 研究）2014
- Deep Learning for Computer Vision - Rob Fergus（纽约大学/Facebook 研究）
- High-dimensional learning with deep network contractions - Stéphane Mallat（高等师范学院）
- Graduate Summer School 2012: Deep Learning, Feature Learning - IPAM, 2012
- Workshop on Big Data and Statistical Machine Learning
- Machine Learning Summer School - 雷克雅未克，冰岛 2014
- Deep Learning Session 1 - Yoshua Bengio（蒙特利尔大学）
- Deep Learning Session 2 - Joshua Bengio（蒙特利尔大学）
- Deep Learning Session 3 - Joshua Bengio（蒙特利尔大学）
Software¶
Annotation tools¶
External Resource Links¶
- Computer Vision Resources - Jia-Bin Huang (UIUC)
- Computer Vision Algorithm Implementations - 简历论文
- Source Code Collection for Reproducible Research - Xin Li（西弗吉尼亚大学）
- CMU Computer Vision Page
General Purpose Computer Vision Library¶
- Open CV
- mexopencv
- SimpleCV
- Open source Python module for computer vision
- ccv: A Modern Computer Vision Library
- VLFeat
- Matlab Computer Vision System Toolbox
- Piotr's Computer Vision Matlab Toolbox
- PCL: Point Cloud Library
- ImageUtilities
Multiple-view Computer Vision¶
- MATLAB Functions for Multiple View Geometry
- Peter Kovesi's Matlab Functions for Computer Vision and Image Analysis
- OpenGV - 几何计算机视觉算法
- MinimalSolvers - 最小的问题解决者
- Multi-View Environment
- Visual SFM
- Bundler SFM
- openMVG: open Multiple View Geometry - 多视图几何； 来自 Motion 库和软件的结构
- Patch-based Multi-view Stereo V2
- Clustering Views for Multi-view Stereo
- Floating Scale Surface Reconstruction
- Large-Scale Texturing of 3D Reconstructions
- Awesome 3D reconstruction list
Feature Detection and Extraction¶
- VLFeat
- SIFT
- David G. Lowe，“来自尺度不变关键点的独特图像特征”，国际计算机视觉杂志，60， 2 (2004)，第 91-110 页.
- SIFT++
- BRISK
- Stefan Leutenegger、Margarita Chli 和 Roland Siegwart，“BRISK：二进制稳健不变可扩展关键点”，ICCV 2011
- SURF
- Herbert Bay、Andreas Ess、Tinne Tuytelaars、Luc Van Gool，“SURF：加速稳健特征”，计算机视觉和图像理解 (CVIU)，卷. 110，第 3 期，第 346--359 页，2008 年
- FREAK
- A. Alahi、R. Ortiz 和 P. Vandergheynst，“FREAK：快速视网膜关键点”，CVPR 2012
- AKAZE
- Paul F. Sewer、Adrien Bartoli 和 Andrew J. Davison，“KAZE 功能”，ECCV
- Local Binary Patterns
High Dynamic Range Imaging¶
Semantic Segmentation¶
Low-level Vision¶
Stereo Vision¶
- Middlebury Stereo Vision
- The KITTI Vision Benchmark Suite
- LIBELAS: Library for Efficient Large-scale Stereo Matching
- Ground Truth Stixel Dataset
Optical Flow¶
- Middlebury Optical Flow Evaluation
- MPI-Sintel Optical Flow Dataset and Evaluation
- The KITTI Vision Benchmark Suite
- HCI Challenge
- Coarse2Fine Optical Flow - Ce Liu (MIT)
- Secrets of Optical Flow Estimation and Their Principles
- C++/MatLab Optical Flow by C. Liu (based on Brox et al. and Bruhn et al.)
- Parallel Robust Optical Flow by Sánchez Pérez et al.
Image Denoising¶
BM3D, KSVD,
Super-resolution¶
- Multi-frame image super-resolution
- Pickup, LC Machine Learning in Multi-frame Image Super-resolution, 博士论文 2008
- Markov Random Fields for Super-Resolution
- W. T Freeman 和 C. Liu. 用于超分辨率和纹理合成的马尔可夫随机场. 摘自 A. Blake、P. Kohli 和 C. Rother 编着的《用于视觉和图像处理的马尔可夫随机场的进展》，第 10 章.麻省理工学院出版社，2011 年
- Sparse regression and natural image prior
- KI Kim 和 Y. Kwon，“使用稀疏回归和自然图像先验的单图像超分辨率”，IEEE Trans. 模式分析与机器智能，卷. 32，没有. 6，第 1127-1133 页，2010 年.
- Single-Image Super Resolution via a Statistical Model
- T. Peleg 和 M. Elad，基于单幅图像超分辨率稀疏表示的统计预测模型，IEEE 图像处理汇刊，卷. 23，第 6 期，第 2569-2582 页，2014 年 6 月
- Sparse Coding for Super-Resolution
- R. Zeyde、M. Elad 和 M. Protter On Single Image Scale-Up using Sparse-Representations, Curves & Surfaces，法国阿维尼翁，2010 年 6 月 24-30 日（也出现在 Lecture-Notes-on-Computer-科学 - LNCS）.
- Patch-wise Sparse Recovery
- Jianchao Yang、John Wright、Thomas Huang 和 Yi Ma. 通过稀疏表示的图像超分辨率. IEEE 图像处理交易 (TIP)，卷. 19，2010 年第 11 期.
- Neighbor embedding
- H. Chang、DY Yeung、Y. Xiong. 通过邻居嵌入的超分辨率. IEEE 计算机协会计算机视觉和模式识别 (CVPR) 会议论文集，第 1 卷，第 275-282 页，美国华盛顿特区，2004 年 6 月 27 日至 7 月 2 日.
- Deformable Patches
- Yu Zhu, Yanning Zhang and Alan Yuille, Single Image Super-resolution using Deformable Patches, CVPR 2014
- SRCNN
- Chao Dong、Chen Change Loy、Kaiming He、Xiaoou Tang，学习用于图像超分辨率的深度卷积网络，ECCV 2014
- A+: Adjusted Anchored Neighborhood Regression
- R. Timofte、V. De Smet 和 L. Van Gool. A+：调整后的锚定邻域回归以实现快速超分辨率，ACCV 2014
- Transformed Self-Exemplars
- Jia-Bin Huang、Abhishek Singh 和 Narendra Ahuja，使用转换后的自样本的单图像超分辨率，IEEE 计算机视觉和模式识别会议，2015 年
Image Deblurring¶
非盲解卷积 * Spatially variant non-blind deconvolution * Handling Outliers in Non-blind Image Deconvolution * Hyper-Laplacian Priors * From Learning Models of Natural Image Patches to Whole Image Restoration * Deep Convolutional Neural Network for Image Deconvolution * Neural Deconvolution
盲解卷积 * Removing Camera Shake From A Single Photograph * High-quality motion deblurring from a single image * Two-Phase Kernel Estimation for Robust Motion Deblurring * Blur kernel estimation using the radon transform * Fast motion deblurring * Blind Deconvolution Using a Normalized Sparsity Measure * Blur-kernel estimation from spectral irregularities * Efficient marginal likelihood optimization in blind deconvolution * Unnatural L0 Sparse Representation for Natural Image Deblurring * Edge-based Blur Kernel Estimation Using Patch Priors * Blind Deblurring Using Internal Patch Recurrence
非均匀去模糊 * Non-uniform Deblurring for Shaken Images * Single Image Deblurring Using Motion Density Functions * Image Deblurring using Inertial Measurement Sensors * Fast Removal of Non-uniform Camera Shake
Image Completion¶
Image Retargeting¶
Alpha Matting¶
- Alpha Matting Evaluation
- Closed-form image matting
- Spectral Matting
- Learning-based Matting
- Improving Image Matting using Comprehensive Sampling Sets
Image Pyramid¶
Edge-preserving image processing¶
- Fast Bilateral Filter
- O(1) Bilateral Filter
- Recursive Bilateral Filtering
- Rolling Guidance Filter
- Relative Total Variation
- L0 Gradient Optimization
- Domain Transform
- Adaptive Manifold
- Guided image filtering
Intrinsic Images¶
- Recovering Intrinsic Images with a global Sparsity Prior on Reflectance
- Intrinsic Images by Clustering
Contour Detection and Image Segmentation¶
- Mean Shift Segmentation
- Graph-based Segmentation
- Normalized Cut
- Grab Cut
- Contour Detection and Image Segmentation
- Structured Edge Detection
- Pointwise Mutual Information
- SLIC Super-pixel
- QuickShift
- TurboPixels
- Entropy Rate Superpixel
- Contour Relaxed Superpixels
- SEEDS
- SEEDS Revised
- Multiscale Combinatorial Grouping
- Fast Edge Detection Using Structured Forests
Interactive Image Segmentation¶
- Random Walker
- Geodesic Segmentation
- Lazy Snapping
- Power Watershed
- Geodesic Graph Cut
- Segmentation by Transduction
Video Segmentation¶
- Video Segmentation with Superpixels
- Efficient hierarchical graph-based video segmentation
- Object segmentation in video
- Streaming hierarchical video segmentation
Camera calibration¶
- Camera Calibration Toolbox for Matlab
- Camera calibration With OpenCV
- Multiple Camera Calibration Toolbox
Simultaneous localization and mapping¶
SLAM community:¶
Tracking/Odometry:¶
- LIBVISO2: C++ Library for Visual Odometry 2
- PTAM: Parallel tracking and mapping
- KFusion: Implementation of KinectFusion
- kinfu_remake: Lightweight, reworked and optimized version of Kinfu.
- LVR-KinFu: kinfu_remake based Large Scale KinectFusion with online reconstruction
- InfiniTAM: Implementation of multi-platform large-scale depth tracking and fusion
- VoxelHashing: Large-scale KinectFusion
- SLAMBench: Multiple-implementation of KinectFusion
- SVO: Semi-direct visual odometry
- DVO: dense visual odometry
- FOVIS: RGB-D visual odometry
Graph Optimization:¶
- GTSAM: General smoothing and mapping library for Robotics and SFM ——佐治亚理工学院
- G2O: General framework for graph optomization
Loop Closure:¶
- FabMap: appearance-based loop closure system - 也可用于 OpenCV2.4.11
- DBoW2: binary bag-of-words loop detection system
Localization & Mapping:¶
Single-view Spatial Understanding¶
- Geometric Context - 德里克·霍伊姆 (CMU)
- Recovering Spatial Layout 瓦尔沙赫道 (UIUC)
- Geometric Reasoning - 大卫·李 (CMU)
- RGBD2Full3D - Ruiqi Guo (UIUC)
Object Detection¶
- INRIA Object Detection and Localization Toolkit
- Discriminatively trained deformable part models
- VOC-DPM
- Histograms of Sparse Codes for Object Detection
- R-CNN: Regions with Convolutional Neural Network Features
- SPP-Net
- BING: Objectness Estimation
- Edge Boxes
- ReInspect
Nearest Neighbor Search¶
General purpose nearest neighbor search¶
- ANN: A Library for Approximate Nearest Neighbor Searching
- FLANN - Fast Library for Approximate Nearest Neighbors
- Fast k nearest neighbor search using GPU
Nearest Neighbor Field Estimation¶
- PatchMatch
- Generalized PatchMatch
- Coherency Sensitive Hashing
- PMBP: PatchMatch Belief Propagation
- TreeCANN
Visual Tracking¶
- Visual Tracker Benchmark
- Visual Tracking Challenge
- Kanade-Lucas-Tomasi Feature Tracker
- Extended Lucas-Kanade Tracking
- Online-boosting Tracking
- Spatio-Temporal Context Learning
- Locality Sensitive Histograms
- TLD: Tracking - Learning - Detection
- CMT: Clustering of Static-Adaptive Correspondences for Deformable Object Tracking
- Kernelized Correlation Filters
- Accurate Scale Estimation for Robust Visual Tracking
- Multiple Experts using Entropy Minimization
- TGPR
- CF2: Hierarchical Convolutional Features for Visual Tracking
- Modular Tracking Framework
Saliency Detection¶
Attributes¶
Action Reconition¶
Egocentric cameras¶
Human-in-the-loop systems¶
Image Captioning¶
Optimization¶
- Ceres Solver - 非线性最小二乘问题和无约束优化求解器
- NLopt- 非线性最小二乘问题和无约束优化求解器
- OpenGM - 基于因子图的离散优化和推理求解器
- GTSAM - 基于因子图的租赁平方优化求解器
Deep Learning¶
Machine Learning¶
- Awesome Machine Learning
- Bob: a free signal processing and machine learning toolbox for researchers
- LIBSVM -- A Library for Support Vector Machines
Datasets¶
External Dataset Link Collection¶
- CV Datasets on the web - 简历论文
- Are we there yet? - 哪篇论文在标准数据集 X 上提供了最好的结果？
- Computer Vision Dataset on the web
- Yet Another Computer Vision Index To Datasets
- ComputerVisionOnline Datasets
- CVOnline Dataset
- CV datasets
- visionbib
- VisualData
Low-level Vision¶
Stereo Vision¶
- Middlebury Stereo Vision
- The KITTI Vision Benchmark Suite
- LIBELAS: Library for Efficient Large-scale Stereo Matching
- Ground Truth Stixel Dataset
Optical Flow¶
- Middlebury Optical Flow Evaluation
- MPI-Sintel Optical Flow Dataset and Evaluation
- The KITTI Vision Benchmark Suite
- HCI Challenge
Video Object Segmentation¶
Change Detection¶
- Labeled and Annotated Sequences for Integral Evaluation of SegmenTation Algorithms
- ChangeDetection.net
Image Super-resolutions¶
Intrinsic Images¶
- Ground-truth dataset and baseline evaluations for intrinsic image algorithms
- Intrinsic Images in the Wild
- Intrinsic Image Evaluation on Synthetic Complex Scenes
Material Recognition¶
Multi-view Reconsturction¶
Saliency Detection¶
Visual Tracking¶
- Visual Tracker Benchmark
- Visual Tracker Benchmark v1.1
- VOT Challenge
- Princeton Tracking Benchmark
- Tracking Manipulation Tasks (TMT)
Visual Surveillance¶
Saliency Detection¶
Change detection¶
Visual Recognition¶
Image Classification¶
Self-supervised Learning¶
Scene Recognition¶
Object Detection¶
Semantic labeling¶
Multi-view Object Detection¶
Fine-grained Visual Recognition¶
Pedestrian Detection¶
Action Recognition¶
Image-based¶
Video-based¶
Image Deblurring¶
Image Captioning¶
Scene Understanding¶
# SUN RGB-D - RGB-D 场景理解基准套件 # NYU depth v2 - RGBD 图像的室内分割和支持推理
Aerial images¶
# Aerial Image Segmentation - 从在线地图学习航拍图像分割
Resources for students¶
Resource link collection¶
- Resources for students - 弗雷多杜兰德（麻省理工学院）
- Advice for Graduate Students - 亚伦赫兹曼（Adobe Research）
- Graduate Skills Seminars - Yashar Ganjali、Aaron Hertzmann（多伦多大学）
- Research Skills - 西蒙·佩顿·琼斯（微软研究院）
- Resource collection - Tao Xie (UIUC) and Yuan Xie (UCSB)
Writing¶
- Write Good Papers - 弗雷多杜兰德（麻省理工学院）
- Notes on writing - 弗雷多杜兰德（麻省理工学院）
- How to Write a Bad Article - 弗雷多杜兰德（麻省理工学院）
- How to write a good CVPR submission - 威廉·弗里曼 (麻省理工学院)
- How to write a great research paper - 西蒙·佩顿·琼斯（微软研究院）
- How to write a SIGGRAPH paper - SIGGRAPH ASIA 2011课程
- Writing Research Papers - 亚伦赫兹曼（Adobe Research）
- How to Write a Paper for SIGGRAPH ——吉姆·布林
- How to Get Your SIGGRAPH Paper Rejected - Jim Kajiya（微软研究院）
- How to write a SIGGRAPH paper - Li-Yi Wei (The University of Hong Kong)
- How to Write a Great Paper - Martin Martin Hering Hering--Bertram（不来梅应用科学大学）
- How to have a paper get into SIGGRAPH? - Takeo Igarashi（东京大学）
- Good Writing - Marc H. Raibert（波士顿动力公司）
- How to Write a Computer Vision Paper - 德里克·霍伊姆 (UIUC)
- Common mistakes in technical writing - Wojciech Jarosz（达特茅斯学院）
Presentation¶
- Giving a Research Talk - 弗雷多杜兰德（麻省理工学院）
- How to give a good talk - David Fleet（多伦多大学）和 Aaron Hertzmann（Adobe Research）
- Designing conference posters - 科林普林顿
Research¶
- How to do research - 威廉·弗里曼 (麻省理工学院)
- You and Your Research ——理查德·海明
- Warning Signs of Bogus Progress in Research in an Age of Rich Computation and Information - Yi Ma (UIUC)
- Seven Warning Signs of Bogus Science - 罗伯特·L·帕克
- Five Principles for Choosing Research Problems in Computer Graphics - Thomas Funkhouser（康奈尔大学）
- How To Do Research In the MIT AI Lab -大卫查普曼（麻省理工学院）
- Recent Advances in Computer Vision - Ming-Hsuan Yang (UC Merced)
- How to Come Up with Research Ideas in Computer Vision? - Jia-Bin Huang (UIUC)
- How to Read Academic Papers - Jia-Bin Huang (UIUC)
Time Management¶
- Time Management - 兰迪·波许 (CMU)
Blogs¶
- Learn OpenCV - 萨蒂亚马利克
- Tombone's Computer Vision Blog - 托马斯·马利谢维奇
- Computer vision for dummies -Vincent Spruyt
- Andrej Karpathy blog - 安德烈·卡帕西
- AI Shack - 乌特卡什·辛哈
- Computer Vision Talks - Eugene Khvedchenya
- Computer Vision Basics with Python Keras and OpenCV - Jason Chin（西安大略大学）
Links¶
- The Computer Vision Industry - 大卫·洛
- German Computer Vision Research Groups & Companies
- awesome-deep-learning
- awesome-machine-learning
- Cat Paper Collection
- Computer Vision News *
Songs¶
Licenses¶
License
在法律允许的范围内， Jia-Bin Huang 已放弃该作品的所有版权和相关或邻接权.