dragonbook / computervisionreadinglist

My reading list for topics in Computer Vision

ComputerVisionReadingList

My reading list for topics in Computer Vision

This list is divided into two main sections, viz. Geometry-based Methods in Vision and Learning-based Methods in Vision.

Research Papers

SfM

1. Multi-stage SfM: A Coarse-to-Fine Approach for 3D Reconstruction
2. Metrics for 3D Rotation: Comparison and Analysis
3. Analyzing 3D Objects in Cluttered Images - NRSfM applied on Cars
4. NRSfM Tutorial
5. Shape and motion from image streams under orthography: A factorization method - Seminal Work on Factorization based Approaches for Structure Recovery
6. Recovering non-rigid 3D shape from image streams - Seminal work on representing non-rigid structure as a combination of basis

Geometry-based Methods in Vision

Course Materials

1. Mathematical Foundations of Graphics and Vision - Good resources on the geometry of SO(3) and on Variational Methods

Learning-based Methods in Vision

Review Notes

1. Review lectures - before you take a grad course in ML

Books

1. [Computer Vision: Models, Learning, and Inference] (http://web4.cs.ucl.ac.uk/staff/s.prince/book/book.pdf)

2. [Computer Vision: Models, Learning, and Inference (Algorithms Booklet)] (http://www0.cs.ucl.ac.uk/external/s.prince/book/Algorithms.pdf)

3. [Computer Vision: Models, Learning, and Inference (Answers Booklet for Students)] (http://www0.cs.ucl.ac.uk/external/s.prince/book/AnswerBookletStudents.pdf)

Lecture Notes

Gaussian Mixture Models and EM

1. Robert Collin's lectures

a. [Gaussian Mixtures and the EM Algorithm] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/EMLectureFeb3.pdf)

b. [EM Clarification] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/EMclarifyPXZ.pdf)

c. [EM Derivation, Proof that EM works] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/cse586emDerivation.pdf)

d. [GMM and K-Means] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/cse586gmmemPart1.pdf)

e. [GMM and EM Intro] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/cse586gmmemPart2.pdf)

f. [Mixture of Gaussians Lecture] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/lectureMixGauIntro.pdf)

2. [Mixture of Gaussians Tutorial - Reynolds] (http://www.ee.iisc.ernet.in/new/people/faculty/prasantg/downloads/GMM_Tutorial_Reynolds.pdf)

3. [Mixture Models and the EM Algorithm - C. Bishop] (http://mlg.eng.cam.ac.uk/tutorials/06/cb.pdf)

4. [Estimating Gaussian Mixture Densities with EM: A Tutorial - Tomasi] (http://www.cse.psu.edu/~rtc12/CSE586/papers/emTomasiTutorial.pdf)

5. [A Short Tutorial on GMMs] (http://www.computerrobotvision.org/2010/tutorial_day/GMM_said_crv10_tutorial.pdf)

6. [A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for GMMs and HMMs] (http://lasa.epfl.ch/teaching/lectures/ML_Phd/Notes/GP-GMM.pdf)

7. [Tutorial on Mixture Models] (http://www.homepages.ucl.ac.uk/~ucakche/presentations/cladagtutorial.pdf)

8. [Mixture Models and EM] (http://www.cs.toronto.edu/~kyros/courses/2503/Handouts/mixtureModel.pdf)

9. [Mixture of Gaussians Tutorial] (https://www.spsc.tugraz.at/system/files/mixtgaussian.pdf)

10. [An Introduction to Mixture Models - Frank Picard] (http://www.informatica.uniroma2.it/upload/2009/IM/mixture-tutorial.pdf)

11. [Mixture Models] (http://www.stat.cmu.edu/~cshalizi/uADA/12/lectures/ch20.pdf)

12. [A Unifying Review of Linear Gaussian Models] (http://mlg.eng.cam.ac.uk/zoubin/papers/lds.pdf)

Introduction to Graphical Models

1. Robert Collin's lectures

a. [Introduction to Graphical Models, Belief Propagation] (http://www.cse.psu.edu/~rtc12/CSE586/lectures/cse586GMplusMP.pdf)