dd

Special Topics in Computer Vision EECS 598

Instructor: Prof. Silvio Savarese
Webpage: http://www.eecs.umich.edu/~silvio/

Classroom: Dow 1005
Time: T Th 1:30pm-3:00pm
Office hours: T 3:00-4:00pm

 

-------------------------------------------------------------------------------------------------------------------

EECS 598- Schedule (subject to changes)

 

 
Lect. Date Topic Details Presenter Papers/slides
           
1 Tues 1.13 Introduction Introduction; 1. S. Savarese PDF
2 Thur 1.15 Multiview geometry I Review of Epipolar geometry & Structure from Motion 2. S. Savarese PDF
3 Tues 1.20 Multiview geometry II 3D reconstruction; Photo tourism; Exploring collections of photographs

3. Hunter Brown & Gaurav Pandey

SLIDES: PDF

  1. M. Brown and D. G. Lowe. "Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets". pdf
  2. Noah Snavely, Steven M. Seitz, Richard Szeliski, "Modeling the world from Internet photo collections," pdf
  3. Noah Snavely, Rahul Garg, Steven M. Seitz, and Richard Szeliski. "Finding Paths through the World's Photos". pdf
4 Thur 1.22 Multiview geometry III Large-Scale Urban
3D Reconstruction; 4D-cities project.

4. Saikrishnan Ramachandran & Matteo Mannino

SLIDES: PDF1; PDF2

  1. J. Hu, S. You, and U. Neumann, " Approaches to Large-Scale Urban Modeling"; pdf
  2. C. Frueh and A. Zakhor, "Constructing 3D City Models by Merging Ground-Based and Airborne Views"; pdf
  3. G. Schindler, F. Dellaert, S.B. Kang, "Inferring Temporal Order of Images From 3D Structure" pdf
  4. http://www.cc.gatech.edu/4d-cities/dhtml/index.html
5 Tues 1.27 Registration of 3D points Handling 3D range data; Registration and matching

5. Tianhe Yang & Bhargav Ramana Avasarala

SLIDES: PDF1; PDF2

  1. P.J. Besl &N.D. McKay, " A Method for Registration of 3-D Shapes"; PDF
  2. Peter J. Neugebauer,"Geometrical Cloning of 3D Objects via Simultaneous Registration of Multiple"; PDF
    Range Images"
  3. S. Rusinkiewicz & M. Levoy, " Efficient Variants of the ICP Algorithm"; PDF
6 Thur 1.29 Descriptors and 3D shape matching (I) Matching shapes with Global descriptors

6. Paritosh Gupta & Ryan Amundsen

SLIDES: PDF1; PDF2; PDF3; PDF4

  1. J. Tangelde, R.  Veltkam,"A survey of content based 3D shape retrieval methods", PDF
  2. M. Kazhdan et al, "Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors", PDF
  3. R. Osada, "Shape distributions", PDF
  4. http://shape.cs.princeton.edu
7 Tues 2.3 no class no class -  
8 Thur 2.5 Descriptors and 3D shape matching (II) Matching shapes with local descriptors; Recognizing 3D objects in cluttered scenes

7. Wongun Choi & Khuram Shahid

SLIDES: PDF1; PDF2

  1. A. Johnson and M. Hebert, " Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes", PDF
  2. S. Belongie, J. Malik and J. Puzicha, "Shape Matching and Object Recognition Using Shape Contexts" PDF
  3. A. Frome et al, "Recognizing Objects in Range Data Using
    Regional Point Descriptors", PDF
9 Tues 2.10 Single instance 3D object recognition (I) Matching 3d models to images; pose estimation

8. Liang Mei & Byung Soo Kim

SLIDES: PDF1; PDF2

  1. Rothganger et al, "3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints"; PDF
  2. Rothganger et al. "Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects"; PDF
10 Thur 2.12 Single instance 3D object recognition (II) eigenvalues methods; SVM methods for 3D object recognition

9. Michael Allison & Joseph Harman

SLIDES: PDF1; PDF2

  1. Murase and Nayar, "Visual Learning and Recognition of 3-D Objects from Appearance" PDF
  2. M Pontil, A Verri, "Support vector machines for 3D object recognition," PDF
  3. http://www.support-vector.net/icml-tutorial.pdf
11 Tues 2.17 Single instance 3D object recognition (III) SIFT and generalized Hough transform methods

10. Jason Clamons & Katherine Scott

SLIDES: PDF1; PDF2; PDF3

  1. D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", PDF
  2. H. Wolfson, "Geometric Hashing: An Overview", PDF
  3. Ballard, "Generalizing the hough transform to detect arbitrary shapes", PDF
12 Thur 2.19 Learning from imagery & 3D data Detector and descriptors for multi-view recognition

11. Hunter Brown & Gaurav Pandey

SLIDES: PDF1

  1. K. MIKOLAJCZYK & C. SCHMID, " Scale & Affine Invariant Interest Point Detectors", PDF
  2. P. Moreels & P.Perona, "Evaluation of Features Detectors and Descriptors based on 3D Objects", PDF
  Tues 2.24   Spring break    
  Thur 2.26   Spring break    
13 Tues 3.3 Scene & object recognition I Introduction 12. S. Savarese PDF
14 Thur 3.5 Scene & Object Recognition II SVM methods; pyramid matching kernels;

13. Saikrishnan Ramachandran & Matteo Mannino

SLIDES:

  1. reference: http://www.support-vector.net/icml-tutorial.pdf
  2. K. Grauman and T. Darrell, "The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features", PDF
  3. S. Lazebnik et al, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories". PDF
15 Tues 3.10 no class no class -  
16 Thur 3.12 Scene & Object Recognition III LDA/PLSA methods; Bag of world models

14. Liang Mei & Byung Soo Kim

SLIDES:

  1. "L. Fei-Fei & P. Perona, "A Bayesian Hierarchical Model for Learning Natural Scene Categories"; PDF
  2. J. Sivic et al, " Discovering objects and their location in images"; PDF
  3. reference: D. Blei et al, "Latent Dirichlet Allocation"; PDF
17 Tues 3.17 Object tracking I Object tracking

15. Paritosh Gupta & Ryan Amundsen

SLIDES:

  1. http://www.cse.psu.edu/~rcollins/CSE598G/introMeanShift.pdf
  2. D. Comaniciu & P. Meer, " Mean shift: a robust approach toward feature space analysis"; PDF
  3. D. Comaniciu et al. "Kernel-Based Object Tracking"; PDF
18 Thur 3.19 Object tracking II Tracking humans and understanding their actions 16. Prof. Fei-Fei Li, Princeton University Special guest lecture
19 Tues 3.24 Scene & Object Recognition IV Part based models 17. Wongun Choi & Khuram Shahid
  1. reference: http://lear.inrialpes.fr/people/schmid/sicile/fergus.pdf
  2. reference: http://www.cc.gatech.edu/~dellaert/em-paper.pdf
  3. Fergus et al. "Object Class Recognition by Unsupervised Scale-Invariant Learning" PDF
  4. Leibe et al " Combined Object Categorization and Segmentation
    with an Implicit Shape Model" PDF
20 Thur 3.26 class postponed to Wed Thurs 4.2 no class -

-

21 Tues 3.31 Scene & Object Recognition V Multi-view models 18. S. Savarese  
22 Thur 4.2 Scene & Object Recognition V Adaboost; sharing features; Learning visual categories 19-20. Tianhe Yang, Bhargav Ramana, Avasarala, Michael Allison and Joseph Harman
  1. reference adaboost: lecture 22
  2. reference adaboost: matas lecture
  3. reference: Freund & Schapire "A Short Introduction to Boosting"
  4. Viola et al. "Detecting Pedestrians Using Patterns of Motion and Appearance", PDF
  5. Torralba et al. "Sharing features: efficient boosting procedures for multiclass object detection" PDF
  6. Opelt et al. "Incremental learning of object detectors using a visual shape alphabet" PDF
23 Tues 4.7 Recognition and reconstruction: Closing the looping I Objects in perspective 21. Jason Clamons & Katherine Scott
  1. Hoiem et al. "Recovering Surface Layout from an Image" PDF
  2. Hoiem et al., “Putting Objects in Perspective”, PDF
24 Thur 4.9 Recognition and reconstruction: Closing the looping II Cognitive loop 22. Byung Soo Kim & Paritosh Gupta
  1. Reference: http://www.vision.ee.ethz.ch/~aess/cvpr2008/
  2. Reference: http://www.vision.ee.ethz.ch/~bleibe/cvpr07/
  3. Leibe et al."Dynamic 3D Scene Analysis from a Moving Vehicle", PDF
  4. Ess et al. "A Mobile Vision System for Robust Multi-Person Tracking", PDF
25 Tues 4.14 Final Project Presentations  
  • Liang
  • Matteo
  • Joseph
 
26 Thur 4.16 Final Project Presentations  
  • Wongun, Khuram
  • Michael; Tianhe;Bhargav
  • Byung
 
27 Friday 4.24 Final Project Presentations  
  • Gaurav
  • Paritosh
  • Ryan
 
  Mon 4.27 Project final report due