CS 342: Computational Photography

http://www.cs.bc.edu/~hjiang/c342/

 CS 342: Computational Photography

INSTRUCTOR: Hao Jiang (Office hours: Thursdays 3:00-4:00pm, Campanella way 554)
SEMESTER: Fall 2010
LOCATION: Futon Hall 453
TIME: T TH 1:30--2:45 PM

Course Overview:

How can we merge multiple pictures to generate a wide-angle view panorama? How can we remove a specific object and fill the hole in an image?How can we generate a 3D walk-through from a single image?Computational photography converges photography, computer vision and computer graphics. It uses computational methods to overcome limitations of traditional photography and video capturing. In this course, we study how to use photos and videos to generate compelling computer imagery. Several popular image-based algorithms will be presented, with an emphasis on using these techniques in real applications. In the programming assignments, students will have the opportunity to acquire their own images and develop the image analysis and synthesis tools to render the scenes.

Syllabus

Notes

Projects

Project 1: Image Alignment (Results from students: Brett, Chris, Jordan, Kevin, Lauren, Matt )

Project 2: Image Retargeting (Results from students: Brett1, Chris1, Hanyin1, Jordan1, Kevin1, Lauren1, Matt1, Chris2, Hanyin2, Jordan2, Kevin2, Lauren2, Matt2 )

Project 3: Image Morphing and Homography (Due day: Nov.2, 2010) (Results from students: Brett, Chris, Hanyin1, Jordan, Kevin, Lauren, Matt)

Project 4: Image Mosaicing (Due day: Nov.17, 2010) (Copy sift_windows.m to sift.m in the skeleton code if you use windows). (Results from students: Brett, Chris, Hanyin, Jordan, Matt)    

ｆｒｏｍ：　http://www.cs.bc.edu/~hjiang/c342/notes.html

Lecture 1: Introduction

• Slides: PDF
• Matlab Tutorial

Lecture 2: Camera and Digital Image

• Slides: PDF
• The vertigo video from Alexei Efros

Lecture 3 Image filtering

• Slides: PDF

Lecture 4 Image Processing, Color

• Slides: PDF
• The template matching code: detect.m and objfilt.m. The test images one and two and the template image.

Lecture 5 Image Pyramid

• The pyramid demo code pyramid.m
• The multi-band blending code mblend.m
• Reference paper: Peter J. Burt, Edward H. Adelson, A Multiresolution Spline With Application to Image Mosaics.

Lecture 6 Entropy

• The entropy code entropy.m
• The Huffman coding code huffman.m and the test script test_huffman2.m
• Reference paper: Peter J. Burt, Edward H. Adelson, The Laplacian Pyramid as a Compact Image Code.

Lecture 7,8 Seem Carving

• Reference paper: Shai Avidan and Ariel Shamir Seam Carving for Content-Aware Image Resizing.

Lecture 9,10 Warping and Morphing

• About homogeneous coordinates, here is a good introduction.
• Slides: PDF

Lecture 11-12 Model Matching

• Slides: Features
• Slides: Matching-I

Lecture 13-16 Matching and Panorama

• Slides: Matching-II (some slides are from Prof. Efros in CMU)

Lecture 17 Bag of Words and Image Retrieval

• Slides: Bag of Words

Lecture 18 Videos and Actions

• Recognizing actions from a distance

Lecture 19-20 Texture Synthesis

• Slides from CMU

Lecture 21 Video Textures

• Video Texture

Lecture 22 Tour into pictures

• Tour into the picture
• Make3D