Home Schedule Requirements Links

Schedule

Notes:

papers highlited in red are the reading assignment for each lesson

20 March, Estimating scene geometry and discovering objects using a soup of segments.

Speaker:

D. Hoiem, A.A. Efros, and M. Hebert, Automatic Photo Pop-up, ACM SIGGRAPH 2005.

26 March, Level Set Methods for Segmentation

Speaker:

Tammy Riklin Raviv

Ron Kimmel, Fast Edge Integration. See reading instructions in the homepage to help you with this paper.

T. Riklin Raviv, N. Kiryati and N. Sochen. Segmentation by Level sets and Symmetry. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2006. to appear.

T. Riklin Raviv, N. Kiryati and N. Sochen. Prior-based Segmentation by Projective Registration and Level sets. IEEE International Conf. on Computer Vision (ICCV), pp 204--211, October 2005.

T. Riklin Raviv, N. Kiryati and N. Sochen. Unlevel-Set: Geometry and Prior-based Segmentation. Proc. of the European Conference on Computer Vision (ECCV), pp.50--61, May 2004.

2 April, Video Visualization

Speaker:

Boykov, Y., Veksler, O.Zabih, R., Fast Approximate Energy Minimization via Graph Cuts, Proc. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-123, 2001. See reading instructions in the homepage to help you with this paper.

J. Assa, Y. Caspi, D. Cohen-Or. Action synopsis: pose selection and illustration. link to site. ACM Trans. Graph. 24(3): 667-676 (2005)

Y. Schnitman, Y. Caspi, D. Cohen-Or, Dani Lischinski. Inducing Semantic Segmentation from an Example. ACCV (2) 2006: 373-384

9 April, Recognition

Speaker:

B.Epshtein, S. Ullman, Feature Hierarchies for Object Classification, ICCV 2005, Beijing, China.

16 April, Passover: No class

23 April, Combining Detection, Recognition and Segmentation

Speakers:

Slides

Read one of these papers:

A. Levin and Y. Weiss. Learning to Combine Bottom-Up and Top-Down Segmentation. Proc. of the European Conference on Computer Vision (ECCV), Graz, Austria, May 2006.

V. Ferrari, T. Tuytelaars, and L. Van Gool. Simultaneous Object Recognition and Segmentation by Image Exploration. In Proc. ECCV, 2004.

Background reading:

E. Borenstein, S. Ullman. Learning to Segment. ECCV (3) 2004: 315-328
E. Borenstein, E. Sharon, S. Ullman, Combining Top-Down and Bottom-Up Segmentation, Proceedings IEEE workshop on Perceptual Organization in Computer Vision, IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, June 2004.

Additional reading:

S. Lazebnik, C. Schmid, and J. Ponce. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories, IEEE Conference on Computer Vision and Pattern Recognition, New York, June 2006, to appear.

30 April, Video Object Segmentation

Speakers:

Slides

Y. Li, J. Sun, H.-Y. Shum. Video object cut and paste. ACM Trans. Graph. 24(3): 595-600 (2005)
J. Wang, P. Bhat, A. Colburn, M. Agrawala, M. Cohen. Interactive Video Cutout. ACM Trans. on Graphics (Proc. of SIGGAPH2005), 2005.

Background:

C. Rother, V. Kolmogorov, and A. Blake. “GrabCut” - interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 23(3):309–314, August 2004.
Y. Li, J. Sun, C.K. Tang and H.Y. Shum. Lazy snapping. Proc. of ACM SIGGRAPH, pp. 303-308, 2004.

7 May, Background Cut

Speakers:

Slides only

slides with movies (zip file)

A. Criminisi, G. Cross, A. Blake and V. Kolmogorov. Bilayer Segmentation of Live Video In Proc. IEEE Computer Vision and Pattern Recognition (CVPR), 2006 New York, US.

V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Rother. Probabilistic fusion of stereo with color and contrast for bi-layer segmentation. Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2006. Preliminary version ("Bi-layer Segmentation of Binocular Stereo Video") appeared in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2005.

J. Sun, W. Zhang, X. Tang and H.-Y. Shum. Background Cut. ECCV 2006

14 May, Hashing, kNN in High Dimensions

Speakers:

Slides

MIT LSH site. See section 3 in user manual.
Application:

G. Shakhnarovich, P. A. Viola, T. Darrell. Fast Pose Estimation with Parameter-Sensitive Hashing. ICCV 2003: 750-759.
B. Georgescu, I. Shimshoni, and P. Meer. Mean shift based clustering in high dimensions: A texture classification example, in Proc. ICCV, Oct. 2003, pp. 456–463.

Theory:

M. Datar, P. Indyk, N. Immorlica and V. Mirrokni. Locality-Sensitive Hashing Scheme Based on p-Stable Distributions. In Proceedings of the Symposium on Computational Geometry, 2004.
Book Chapter from this site: book chapter
A. Gionis, P. Indyk, R. Motwani. Similarity Search in High Dimensions via Hashing. VLDB 1999: 518-529

21 May, Recent Progress in Optical Flow Computation

Speakers:

Slides

T. Brox, A. Bruhn, N. Papenberg, J. Weickert. High Accuracy Optical Flow Estimation Based on a Theory for Warping. ECCV (4) 2004: 25-36
A. Bruhn, J. Weickert, C. Schnorr, Combining the advantages of Local and Global Optic Flow Methods, L. Van Gool (Ed.), Pattern Recognition, Lecture Notes in Computer Science, Vol. 2449, Springer, Berlin, 454-462, 2002.

(long version) A. Bruhn, J. Weickert, C. Schnorr: Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods. International Journal of Computer Vision, Vol. 61, No. 3, 211-231, February/March 2005. Revised version of Technical Report No. 82, Department of Mathematics, Saarland University, Saarbrucken, Germany, April 2003.

Real-Time:

A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger and C. Schnorr: Real-Time Optic Flow Computation with Variational Methods. In N. Petkov, M. A. Westenberg (Eds.): Computer Analysis of Images and Patterns. Lecture Notes in Computer Science, Vol. 2756, Springer, Berlin, 222-229, 2003.
A. Bruhn, J. Weickert. Towards Ultimate Motion Estimation: Combining Highest Accuracy with Real-Time Performance. ICCV 2005: 749-755

28 May, Learning Optical Flow

Speakers:

Slides

S. Roth and M. J. Black. Fields of Experts: A Framework for Learning Image Priors. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 860-867, June 2005.
S. Roth and M. J. Black. On the Spatial Statistics of Optical Flow. International Journal of Computer Vision (IJCV). Marr Prize special issue. In preparation.

4 June, Matting

Speakers:

Slides

J. Wang, M. Cohen. An Iterative Optimization Approach for Unified Image Segmentation and Matting. ICCV 2005(oral paper), Beijing, China.

A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2006, New York

Background:

Y.-Y Chuang, B. Curless, D. Salesin, R. Szeliski. A Bayesian Approach to Digital Matting. CVPR (2) 2001: 264-271
J. Sun, J. Jia, C.-K. Tang, H.-Y. Shum. Poisson matting, in: Proc. ACM SIGGRAPH, 2004, pp. 315–321

11 June, Illumination

Speakers:

Slides

S. M. Seitz, Y. Matsushita, K. N. Kutulakos. A Theory of Inverse Light Transport. ICCV 2005: 1440-1447.

K. N. Kutulakos, E. Steger. A Theory of Refractive and Specular 3D Shape by Light-Path Triangulation. ICCV 2005: 1448-1455

J. Davis, R. Yang, L. Wang. BRDF Invariant Stereo using Light Transport Constancy, IEEE International Conference on Computer Vision (ICCV), 2005.

18 June, CVPR: No class

25 June, Optimization I

Speakers:

Slides

J.S.Yedidia, W.T.Freeman, Y.Weiss, Understanding Belief Propagation and Its Generalizations, Exploring Artificial Intelligence in the New Millennium, Chap. 8, January 2003.

V.Kolmogorov and R.Zabih, What Energy Functions Can be Minimized via Graph Cuts?, IEEE Trans. PAMI, vol. 26, pp. 147--159, 2004

T. Meltzer, C. Yanover, and Y. Weiss. Globally Optimal Solutions for Energy Minimization in Stereo Vision using Reweighted Belief Propagation. In Proceedings International Conference on Computer Vision (ICCV), 2005.

Optional:

R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, C. Rother. A Comparative Study of Energy Minimization Methods for Markov Random Fields, To appear in European Conference on Computer Vision, May 2006.
V. Kolmogorov, C. Rother. Comparison of energy minimization algorithms for highly connected graphs, To appear in European Conference on Computer Vision, May 2006.