Computer Vision Resources

Published: 12 Sep 2015 Category: computer_vision


Mobile Computer Vision (Spring 2015)

CSCI1950-G Computational Photography

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

EECS 432 Advanced Computer Vision

EECS 286 Advanced Topics in Computer Vision

CS280: Computer Vision (University of California Berkeley)

CSCI2951-T Data-driven Computer Vision (Spring 2016)

Images Denoising

Fast Burst Images Denoising

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

Blind Image Denoising via Dependent Dirichlet Process Tree

Image denoising via group sparsity residual constraint

Image Blur / Deblur

Motion Blurred Images Generation

Blind Image Deblurring Using Dark Channel Prior

Good Regions to Deblur


Real-Time Gradient-Domain Painting

Sketch2Photo: Internet Image Montage

Combining Sketch and Tone for Pencil Drawing Production

Image Retrieval

Multi-modal image retrieval with random walk on multi-layer graphs

Content-based image retrieval tutorial

Image Summary

Summarizing Visual Data Using Bidirectional Similarity

Image Retargeting / Editing

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing

The Generalized PatchMatch Correspondence Algorithm

Seamless Image Editing

Image Inpaiting

Patch-based Texture Synthesis for Image Inpainting

Image Dithering

Image Dithering: Eleven Algorithms and Source Code

Image Enhancement

LIME: A Method for Low-light IMage Enhancement

SelPh: Progressive Learning and Support of Manual Photo Color Enhancement

Image Resizing

Image Cloning

Coordinates for Instant Image Cloning

Image Compositing

Interactive Digital Photomontage

Panorama Stitching

CS510 Visual Computing, Project 2: Panorama Stitching

Image Stylization

stylize: Regressor based image stylization

Procedurally Generating Stylized Farmland Scenes

Image Haze Removal

Single Image Haze Removal

DehazeNet: An End-to-End System for Single Image Haze Removal

Image Blending

Linear Blending, Poisson Blending, Multiband Blending, Feather Blending, Alpha Blending, Laplacian Blending

Image Blending

CS 195-G: Image Blending

Panoramic Image Mosaic

Linear Blending

Adding (blending) two images using OpenCV

Poisson Blending

Poisson Image Editing

Poisson Blending

Poisson Blending II

Solving the Discrete Poisson Equation using Jacobi, SOR, Conjugate Gradients, and the FFT

Gradient Domain Fusion Using Poisson Blending

Image Stitching

Natural and Seamless Image Composition with Color Control

Object-aware Gradient-Domain Image Compositing

Improving Image Matting using Comprehensive Sampling Sets

Multi-scale Image Harmonization

Drag-and-Drop Pasting

Cross Dissolve Without Cross Fade: Preserving Contrast, Color and Salience in Image Compositing

Snap Image Composition

Stitching Stabilizer: Two-frame-stitching Video Stabilization for Embedded Systems

Stitching and Matting

Image Stitching

Graphics isn’t all about 3-D

Assignment: Image stitching with RANSAC

OpenCV panorama stitching

Real-time panorama and image stitching with OpenCV

Image Super-Resolution

Super-Resolution From a Single Image

Aperture-scanning Fourier ptychography for 3D refocusing and super-resolution macroscopic imaging

Single Image Super-Resolution from Transformed Self-Exemplars

Photo Collage


Picture Collage

Picture Collage

Efficient Optimization of Photo Collage

Video Collage

Stained-Glass Visualization for Highly Condensed Video Summaries (ICME 2004)

Video collage: A novel presentation of video sequence

Stained Glass Photo Collages

Visual Storylines: Semantic Visualization of Movie Sequence

Video collage: presenting a video sequence using a single image

Efficient Optimization of Photo Collage

Puzzle-like Collage (2010)

Browsing Large Image Datasets through Voronoi Diagrams;jsessionid=576998825C3E40A32826A00B64089DF6?doi=

Content-aware Photo Collage Using Circle Packing

Automatic Generation of Social Media Snippets for Mobile Browsing

Video Tapestry

Digital Tapestry

Video Tapestries with Continuous Temporal Zoom

Video Creativity

6 Seconds of Sound and Vision: Creativity in Micro-Videos

Video Highlights

Ranking Domain-specific Highlights by Analyzing Edited Videos

Salient Montages from Unconstrained Videos

Video Summarization

Creating Summaries from User Videos

Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction

Video Summarization by Learning Submodular Mixtures of Objectives

TVSum: Summarizing Web Videos Using Titles

Summarizing While Recording: Context-Based Highlight Detection for Egocentric Videos

Title Generation for User Generated Videos

Activity Recognition

Latent Hierarchical Model for Activity Recognition

Virtual Reality (VR)

Surround360 System: Facebook’s open source hardware and software for capturing stereoscopic 3D 360 video for VR

Virtual Reality


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


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

The Future of Real-Time SLAM and Deep Learning vs SLAM

Awesome SLAM

ORB-SLAM2: Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities


Introducing Cartographer

Real-Time Loop Closure in 2D LIDAR SLAM

Optical Flow

A Database and Evaluation Methodology for Optical Flow

SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm


Ocular: a state-of-the-art historical OCR system

SESHAT: Handwritten math expression parser

  • intro: Seshat is an open-source system for recognizing handwritten mathematical expressions. Given a sample represented as a sequence of strokes, the parser is able to convert it to LaTeX or other formats like InkML or MathML.
  • github:

Awesome OCR: Links to awesome OCR projects

【OCR/机器学习/搜索引擎】基于 Tesseract的图文识别搜

The Simple + Practical Path to Machine Learning Capability: A Common Benchmark Task

Optical Character Recognition (OCR)

Sharingan: Newspaper text and context extractor


JPEG 101 - How does JPEG work?

Face Alignment

Supervised Descent Method and its Applications to Face Alignment

Face Alignment at 3000 FPS via Regressing Local Binary Features

Joint Cascade Face Detection and Alignment


RGB-W: When Vision Meets Wireless

A Computational Approach for Obstruction-Free Photography

My Text in Your Handwriting

Seeing the Arrow of Time

Time-lapse Mining from Internet Photos

3D Time-lapse Reconstruction from Internet Photos

The Fast Bilateral Solver

Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

Atoms of recognition in human and computer vision

Live Texturing of Augmented Reality Characters from Colored Drawings

Colorization for Image Compression

Face2Face: Real-time Face Capture and Reenactment of RGB Videos


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

FaceDirector: Continuous Control of Facial Performance in Video

Real-time Expression Transfer for Facial Reenactment

Photo Stylistic Brush: Robust Style Transfer via Superpixel-Based Bipartite Graph

GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence


OpenBR: Open Source Biometrics, Face Recognition, Age Estimation, Gender Estimation


Home Surveilance with Facial Recognition

Image unshredding using a TSP solver


Awesome Computer Vision

Resources: Visual Recognition and Search


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

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

FastCV Computer Vision SDK

Video++, a C++14 high performance video and image processing library

VLFeat – Vision Lab Features Library

  • intro: Algorithms include Fisher Vector, VLAD, SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, SLIC superpixels, quick shift superpixels, large scale SVM training, and many others
  • homapage:
  • github:


CVonline: Image Databases

Yet Another Computer Vision Index To Datasets (YACVID)


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

**Unsupervised Computer Vision: The State of the Art Stitch Fix Technology – Multithreaded**

Exploring Computer Vision

Image Processing with Numpy


SIGGRAPH 2016 papers on the web


The Ultimate List of 300+ Computer Vision Resources