Skip to content

机器视觉

Awesome Computer Vision: Awesome

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

Books

Computer Vision

OpenCV Programming

Machine Learning

Fundamentals

Courses

Computer Vision

Computational Photography

Machine Learning and Statistical Learning

Optimization

Papers

Conference papers on the web

Survey Papers

##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

Recent Conference Talks

3D Computer Vision

Internet Vision

Computational Photography

Learning and Vision

Object Recognition

Graphical Models

Machine Learning

Optimization

Deep Learning

Software

Annotation tools

General Purpose Computer Vision Library

Multiple-view Computer Vision

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
Optical Flow
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
Image Pyramid
Edge-preserving image processing

Intrinsic Images

Contour Detection and Image Segmentation

Interactive Image Segmentation

Video Segmentation

Camera calibration

Simultaneous localization and mapping

SLAM community:
Tracking/Odometry:
Graph Optimization:
Loop Closure:
Localization & Mapping:

Single-view Spatial Understanding

Object Detection

Nearest Neighbor Field Estimation

Visual Tracking

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

Datasets

Low-level Vision

Stereo Vision
Optical Flow
Video Object Segmentation
Change Detection
Image Super-resolutions

Intrinsic Images

Material Recognition

Multi-view Reconsturction

Saliency Detection

Visual Tracking

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

Writing

Presentation

Research

Time Management

Blogs

Songs

Licenses

License

CC0

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.