Computer Vision Resources

• Courses
• Edge detection
• Images Denoising
• Deblur
• Painting
• Bag Of Words
• Activity Recognition
• License Plate Recognition
• Image Summary
• Image Retargeting/Editing
• SLAM
• Papers
• Applications
• Resources
• Libraries
• Datasets
• Blogs

Courses

Stanford CS231n: Convolutional Neural Networks for Visual Recognition

• homepage: http://cs231n.stanford.edu/
• homepage: http://vision.stanford.edu/teaching/cs231n/index.html
• syllabus: http://vision.stanford.edu/teaching/cs231n/syllabus.html
• github.io: http://cs231n.github.io/
• youtube: https://www.youtube.com/watch?v=NfnWJUyUJYU&feature=youtu.be
• video: http://pan.baidu.com/s/1pKsTivp

Mobile Computer Vision

http://web.stanford.edu/class/cs231m/

CSCI1950-G Computational Photography

http://cs.brown.edu/courses/csci1950-g/

MIT CSAIL: 6.819/6.869: Advances in Computer Vision (Fall 2015)

• homepage: http://6.869.csail.mit.edu/fa15/index.html

Edge detection

Image-feature-detection-using-Phase-Stretch-Transform

• github: https://github.com/JalaliLabUCLA/Image-feature-detection-using-Phase-Stretch-Transform
• wikipedia: https://en.wikipedia.org/wiki/Phase_stretch_transform

Images Denoising

Fast Burst Images Denoising(SIGGRAPH Asia 2014. CUHK, Microsoft Research)

• paper: http://personal.ie.cuhk.edu.hk/~lz013/papers/burstdenoising.pdf
• project: http://personal.ie.cuhk.edu.hk/~lz013/projects/BurstDenoising.html

Robust non-linear regression analysis: A greedy approach employing kernels and application to image denoising (KGARD)

• arxiv: http://arxiv.org/abs/1601.00595
• code(Matlab): http://bouboulis.mysch.gr/kernels.html

Blind Image Denoising via Dependent Dirichlet Process Tree

• arxiv: http://arxiv.org/abs/1601.03117

Deblur

Good Regions to Deblur

• project page: https://eng.ucmerced.edu/people/zhu/GoodRegion.html
• paper: https://eng.ucmerced.edu/people/zhu/ECCV12.pdf
• code(Matlab): https://eng.ucmerced.edu/people/zhu/ECCV12_code.zip

Painting

Real-Time Gradient-Domain Painting (SIGGRAPH 2009)

• homepage: http://graphics.cs.cmu.edu/projects/gradient-paint/
• paper: http://graphics.cs.cmu.edu/projects/gradient-paint/grad.light.r2226.pdf

RGB-W: When Vision Meets Wireless

• paper: http://vision.stanford.edu/pdf/RGBW_ICCV15.pdf

Computer Vision Datasets

• website: http://clickdamage.com/sourcecode/index.html
• code: http://clickdamage.com/sourcecode/cv_datasets.php
• BaiduPan: http://pan.baidu.com/s/1pJmqD4n

A Computational Approach for Obstruction-Free Photography

• paper: https://people.csail.mit.edu/mrub/papers/ObstructionFreePhotograpy_SIGGRAPH2015.pdf

Bag Of Words

Activity Recognition

Latent Hierarchical Model for Activity Recognition

• paper: http://arxiv.org/abs/1503.01820
• github: https://github.com/louxi11/activity_recognition
• author page: https://staff.fnwi.uva.nl/n.hu/

License Plate Recognition

• website: http://www.openalpr.com/
• github: https://github.com/openalpr/openalpr
• tech reciew: http://arstechnica.com/business/2015/12/new-open-source-license-plate-reader-software-lets-you-make-your-own-hot-list/

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

• arxiv: http://arxiv.org/abs/1601.05610

Image Summary

Summarizing Visual Data Using Bidirectional Similarity

• homepage: http://denis.simakov.info/weizmann/summarization_talk_20101116/summarization.html
• paper: http://www.wisdom.weizmann.ac.il/~vision/VisualSummary/bidirectional_similarity_CVPR2008.pdf

Image Retargeting/Editing

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing

• homepage(paper+code): http://gfx.cs.princeton.edu/pubs/Barnes_2009_PAR/
• paper: http://gfx.cs.princeton.edu/pubs/Barnes_2009_PAR/patchmatch.pdf
• code: http://gfx.cs.princeton.edu/pubs/Barnes_2009_PAR/patchmatch-2.1.zip

The Generalized PatchMatch Correspondence Algorithm

• homapage(paper+code): http://gfx.cs.princeton.edu/pubs/Barnes_2010_TGP/index.php
• paper: http://gfx.cs.princeton.edu/pubs/Barnes_2010_TGP/generalized_pm.pdf
• code: http://www.cs.princeton.edu/gfx/pubs/Barnes_2009_PAR/patchmatch-2.0.zip

SLAM

Why SLAM Matters, The Future of Real-Time SLAM, and Deep Learning vs SLAM

• blog: http://www.computervisionblog.com/2016/01/why-slam-matters-future-of-real-time.html?m=1

一起做RGB-D SLAM

• blog: http://www.cnblogs.com/gaoxiang12/tag/%E4%B8%80%E8%B5%B7%E5%81%9ARGB-D%20SLAM/
• github: https://github.com/gaoxiang12/rgbd-slam-tutorial-gx

PySceneDetect: a command-line application and a Python library for automatically detecting scene changes in video files

• homepage: http://pyscenedetect.readthedocs.org/en/latest/

Papers

Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

• arxiv: http://arxiv.org/abs/1602.00753
• project page: http://grail.cs.washington.edu/projects/size/

Atoms of recognition in human and computer vision

• homepage: http://www.wisdom.weizmann.ac.il/~dannyh/Mircs/mircs.html

Applications

Target acquired: Finding targets in drone and quadcopter video streams using Python and OpenCV

http://www.pyimagesearch.com/2015/05/04/target-acquired-finding-targets-in-drone-and-quadcopter-video-streams-using-python-and-opencv/

Build a Face Detection App Using Node.js and OpenCV

http://www.sitepoint.com/face-detection-nodejs-opencv/

FaceDirector: Continuous Control of Facial Performance in Video

• homepage: http://www.disneyresearch.com/publication/facedirector/
• paper: http://disneyresearch.s3-us-west-1.amazonaws.com/wp-content/uploads/20151210174750/FaceDirector-Continuous-Control-of-Facial-Performance-in-Video-Paper.pdf

Real-time Expression Transfer for Facial Reenactment

• paper: http://graphics.stanford.edu/~niessner/papers/2015/10face/thies2015realtime.pdf
• homepage: http://graphics.stanford.edu/~niessner/thies2015realtime.html

Resources

Awesome-deep-vision: A curated list of deep learning resources for computer vision

• website: http://jiwonkim.org/awesome-deep-vision/
• github: https://github.com/kjw0612/awesome-deep-vision

Awesome Computer Vision

• github: https://github.com/jbhuang0604/awesome-computer-vision

Resources: Visual Recognition and Search

• intro: “Non-exhaustive list of state-of-the-art implementations related to visual recognition and search”
• blog: http://rogerioferis.com/VisualRecognitionAndSearch2014/Resources.html

Libraries

BoofCV: an open source Java library for real-time computer vision and robotics applications

http://boofcv.org/index.php?title=Main_Page

tracking.js: A modern approach for Computer Vision on the web

• homepage: https://trackingjs.com/
• github: https://github.com/eduardolundgren/tracking.js/

Datasets

CVonline: Image Databases

http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm

Yet Another Computer Vision Index To Datasets (YACVID)

http://riemenschneider.hayko.at/vision/dataset/

Blogs

From feature descriptors to deep learning: 20 years of computer vision

• blog: http://www.computervisionblog.com/2015/01/from-feature-descriptors-to-deep.html

• blog: http://multithreaded.stitchfix.com/blog/2016/02/04/computer-vision-state-of-the-art
• slides: http://pan.baidu.com/s/1c0Sxzvq

Exploring Computer Vision

• (Part I): Convolutional Neural Networks: https://indico.io/blog/exploring-computer-vision-convolutional-neural-nets/
• (Part II): Transfer Learning: https://indico.io/blog/exploring-computer-vision-transfer-learning/