CSC2523: Shape Perception in Human and
Computer Vision
Instructor: Sven Dickinson
Each week, there will typically be 2 required readings, all
available electronically on the secure course website (for copyright reasons Ð
youÕll need the access password from the instructor); on one occasion, there
will be three readings, including one very short one. Supplemental readings are provided for those
that are interested in learning more about a given topic; they are not required
reading.
1. Introduction to Shape Perception
No required readings Ð instructor will provide overview of course
and cover all administrative details.
Supplemental:
S.
Dickinson and Z. Pizlo (Eds.), ÒShape Perception in Human and Computer Vision: An Interdisciplinary
PerspectiveÓ, Advances in Computer Vision
and Pattern Recognition Series, Springer Verlag,
2013.
2. Perceptual Grouping: the Foundation of
Shape Perception
A. Witkin and J. Tenenbaum, ÒOn the
role of structure in visionÓ, in Human and
Machine Vision (J. Beck, B. Hope, and A. Rosenfeld, Eds.), pp 481Ð543,
Academic Press, 1983.
http://www.cs.toronto.edu/~sven/2523/Papers/WitkinTenenbaum1983.pdf
Y.
Qi, Y.-Z. Song, T. Xiang, H. Zhang, T. Hospedales, Y.
Li, and J. Guo, ÒMaking Better Use of Edges via
Perceptual GroupingÓ, Proceedings, IEEE Conference on Computer Vision and
Pattern Recognition, 2015.
http://www.cs.toronto.edu/~sven/2523/Papers/Qi2015.pdf
Supplemental:
F. Attneave, ÒSome
Informational Aspects of Visual PerceptionÓ, Psychological Review, Volume 61, Number 3, 1954, pp 183-193.
http://www.cs.toronto.edu/~sven/2523/Papers/Attneave1954.pdf
J. Feldman, ÒBayesian Contour IntegrationÓ, Perception and Psychophysics, Volume 63,
Number 7, 2001, pp 1171-1182.
http://www.cs.toronto.edu/~sven/2523/Papers/feldman_bayes.pdf
J. Wagemans, J.
Elder, M. Kubovy, S. Palmer, M. Peterson, M. Singh,
and R. von der Heydt, ÒA century of Gestalt psychology in visual
perception: I. Perceptual grouping and figure-ground organizationÓ, Psychological Bulletin, Volume 138,
Number 6, 2012, pp 1172-1217.
http://www.cs.toronto.edu/~sven/2523/Papers/WagemansGestalt1.pdf
J. Wagemans,
J. Feldman, S. Gepshtein, R. Kimchi, J. Pomerantz, P. van der Helm, and C.
van Leeuwen,
ÒA Century of Gestalt Psychology in Visual Perception: II. Conceptual and
Theoretical FoundationsÓ, Psychological Bulletin, Volume 138, Number 6, 2012, 1218-1252.
http://www.cs.toronto.edu/~sven/2523/Papers/WagemansGestalt2.pdf
K. Greff, A. Rasmus, M. Berglund, T. H. Hao,
J. Schmidhuber, and H. Valpola,
ÒTagger: Deep unsupervised perceptual groupingÓ, Proceedings, Conference on
Neural Information Processing Systems (NIPS), 2016.
http://www.cs.toronto.edu/~sven/2523/Papers/Greff2016.pdf
3. Separating the Shape from its Background: Contour Closure
J. Elder and
S. Zucker, ÒThe effect of contour closure on the
rapid discrimination of two-dimensional shapesÓ, Vision Research, Volume 33, Number 7, 1993, pp 981-991.
http://www.cs.toronto.edu/~sven/2523/Papers/ElderZucker1993.pdf
A. Levinshtein, C. Sminchisescu, and
S. Dickinson, ÒOptimal Image and Video Closure by Superpixel
GroupingÓ, International Journal of Computer Vision, Volume 100, Number
1, 2012, pp 99-119.
http://www.cs.toronto.edu/~sven/Papers/IJCV-closure.pdf
Supplemental:
I. Kovacs and B. Julesz, ÒA closed curve is much more than an incomplete
one: Effect of closure in figure-ground segmentationÓ, Proc. Natl. Acad. Sci. USA, Volume 90, 1993, pp 7495-7497.
http://www.cs.toronto.edu/~sven/2523/Papers/KovacsJulesz1993.pdf
P. Garrigan,
ÒThe effect of contour closure on shape recognitionÓ, Perception, Volume
41, Number 2, 2012, pp 221-235.
http://www.cs.toronto.edu/~sven/2523/Papers/Garrigan2012.pdf
4. Object-Centered vs Viewer-Centered Shape Perception
R. Shephard and J. Metzler, ÒMental Rotation
of Three-Dimensional ObjectsÓ, Science,
Volume 171, Number 3972, 1971, pp 701-703.
http://www.cs.toronto.edu/~sven/2523/Papers/ShepardMetzler71.pdf
S. Edelman and H. Bulthoff,
ÒOrientation Dependence in the Recognition of Familiar and Novel Views of
Three-Dimensional ObjectsÓ, Vision
Research, Volume 32, Number 12, pp 2385-2400.
http://www.cs.toronto.edu/~sven/2523/Papers/EdelmanBulthoff92.pdf
Supplemental:
E. L. J. Leeuwenberg,
ÒA Perceptual Coding Language for Visual and Auditory PatternsÓ, The American Journal of Psychology,
Volume 84, Number 3, 1971, pp 307-349.
http://www.cs.toronto.edu/~sven/2523/Papers/Leeuwenberg1971.pdf
J. Koenderink and
A. van Doorn, ÒThe Singularities of the Visual
MappingÓ, Biological Cybernetics,
Volume 24, 1976, pp 51-59.
http://www.cs.toronto.edu/~sven/2523/Papers/Koenderink1976.pdf
I. Rock and J. DiVita,
ÒA Case of Viewer-Centered Object PerceptionÓ, Cognitive Psychology, Volume 19, 1987, pp 280-293.
http://www.cs.toronto.edu/~sven/2523/Papers/Rock_Divita_1987.pdf
M. Tarr and S. Pinker, ÒMental rotation and
orientation-dependence in shape recognitionÓ, Cognitive Psychology, Volume 21, 1989, pp 233-282.
http://www.cs.toronto.edu/~sven/2523/Papers/TarrPinker1989.pdf
S.
Ullman and R. Basri, ÒRecognition by linear
combinations of modelsÓ, IEEE
Transactions on Pattern Analysis and Machine Intelligence, Volume 13, 1991,
pp 992-1006.
http://www.cs.toronto.edu/~sven/2523/Papers/Basri91.pdf
S. Dickinson,
A. Pentland, and A. Rosenfeld, Ò3-D Shape Recovery
Using Distributed Aspect MatchingÓ, IEEE
Transactions on Pattern Analysis and Machine Intelligence, Volume 14,
Number 2, 1992, pp 174 - 198.
http://www.cs.toronto.edu/~sven/Papers/pami-aspect.pdf
S. Dickinson, A. Pentland, and A. Rosenfeld, ÒFrom
volumes to views: an approach to 3D object recognitionÓ, CVGIP: Image Understanding, Volume 55, Number 2, 1992, pp 130-154.
http://www.cs.toronto.edu/~sven/Papers/cviu92.pdf
http://www.cs.toronto.edu/~sven/2523/Papers/Logothetis1995.pdf
P. Sinha and T. Poggio,
ÒRole of Learning in three-dimensional form perceptionÓ, Nature, Volume 384, 1996, pp 460-463.
http://www.cs.toronto.edu/~sven/2523/Papers/sinha_poggio_1996.pdf
Z. Pizlo
and A. Stevenson, ÒShape Constancy from Novel ViewsÓ, Perception &
Psychophysics, 1999, 61
(7), pp 1299-1307.
http://www.cs.toronto.edu/~sven/2523/Papers/pizlo-stevenson-99.pdf
Y. Yamane, E. Carlson, K. Bowman, Z. Wang,
and C. Connor, ÒA Neural Code for Three-Dimensional Object Shape in Macaque Inferotemporal CortexÓ, Nature
Neuroscience, Volume 11, Number 11, 2008, pp 1352-1360.
http://www.cs.toronto.edu/~sven/2523/Papers/Yamane2008.pdf
Z. Pizlo,
T. Sawada, Y. Li, W. Kropatsch, and R. Steinman, ÒNew
approach to the perception of 3D shape based on veridicality, complexity,
symmetry and volumeÓ, Vision Research,
Volume 50, 2010, pp 1-11.
http://www.cs.toronto.edu/~sven/2523/Papers/Pizlo2010.pdf
5. Polyhedral Shape Perception
M. Chan, A. Stevenson, Y. Li, and Z. Pizlo,
ÒBinocular shape constancy from novel views: the role of a priori constraintsÓ,
Perception & Psychophysics, Volume 68, 2006, pp 1124-1139.
http://www.cs.toronto.edu/~sven/2523/Papers/Pizlo2006.pdf
D.
Lowe, ÒThree-Dimensional Object Recognition from Single Two-Dimensional Images,
Artificial Intelligence, Volume 31,
Number 3, 1987, pp 355-395.
http://www.cs.toronto.edu/~sven/2523/Papers/lowe.pdf
Supplemental:
L.G.
Roberts, ÒMachine Perception of 3-D SolidsÓ Optical
and Electro-Optical Information Processing, (J. T. Tippet et al., Eds.), 1965,
pp 159-197.
www.packet.cc/files/mach-per-3D-solids.html#*
http://www.cs.toronto.edu/~sven/2523/Papers/RobertsThesis1965.pdf
(thesis)
D. Lowe, ÒThe viewpoint consistency constraintÓ, International Journal of Computer Vision, Volume 1, Number 1, 1987,
pp 57-72.
http://www.cs.toronto.edu/~sven/2523/Papers/lowe.pdf
D. Huttenlocher and S. Ullman, ÒRecognizing Solid Objects by
Alignment with an ImageÓ, International
Journal of Computer Vision, Volume 5, Number 2, 1990, pp 195-212. http://www.cs.toronto.edu/~sven/2523/Papers/huttenlocher.pdf
6. Symmetry as a Basis for 2-D Shape Perception
(Note: the first paper is very short;
therefore, one student will cover the first two, while the second student
covers the third)
I.
Kovacs and B. Julesz, ÒPerceptual Sensitivity Maps
within Globally Defined Visual ShapesÓ, Nature, Volume 370, 1994, pp 644Ð646.
http://www.cs.toronto.edu/~sven/2523/Papers/KovacsJulesz94.pdf
J. Feldman and M. Singh, ÒBayesian estimation
of the shape skeletonÓ, Proceedings of the
National Academy of Sciences, Volume 103, number 47, 2006, pp
18014-18019.
http://www.cs.toronto.edu/~sven/2523/Papers/feldman_singh_skeletons.pdf
A. Levinshtein, C. Sminchisescu, and
S. Dickinson, ÒMultiscale
Symmetric Part Detection and GroupingÓ, International Journal of
Computer Vision, Volume 104, Number 2, 2013, pp 117-134.
http://www.cs.toronto.edu/~sven/2523/Papers/Levinshtein2013.pdf
Supplemental:
H.
Blum, ÒDiscussion Paper: A Geometry for BiologyÓ, Annals of the New York Academy of Sciences, Volume 231, Number 1,
1974, pp 19-30.
http://www.cs.toronto.edu/~sven/2523/Papers/Blum1974.pdf
I. Kovacs, A. Feher,
and B. Julesz, ÒMedial-point description of shape: A
representation for action coding and its psychophysical correlatesÓ, Vision Research, Volume 38, 1998, pp
2323-2333.
http://www.cs.toronto.edu/~sven/2523/Papers/KovacsFeherJulesz98.pdf
B.
Kimia, ÒOn the Role of Medial Geometry in Human VisionÓ, Journal of Physiology Paris, Volume 97, 2003, pp 155-190.
http://www.cs.toronto.edu/~sven/2523/Papers/KimiaPhysiology.pdf
H.
Ling and D. Jacobs, ÒShape Classification Using the Inner-DistanceÓ, IEEE Transactions on Pattern Analysis and
Machine Intelligence, Volume 29, Number 2, 2007, pp 286-299.
http://www.cs.toronto.edu/~sven/2523/Papers/LingJacobs2007.pdf
C.-C.
Hung, E. Carlson, and C. E. Connor, ÒMedial Axis Shape Coding in Macaque Inferotemporal CortexÓ, Neuron,
Volume 74, 2012, pp 1099-1113.
http://www.cs.toronto.edu/~sven/2523/Papers/HungCarlsonConnor2012.pdf
M. Lescroart and I.
Biederman, ÒCortical Representation of Medial Axis
StructureÓ, Cerebral Cortex, Volume
23, 2013, pp 629-637.
http://www.cs.toronto.edu/~sven/2523/Papers/Lescroart2013.pdf
C.
Firestone and B. Scholl, Ò`Please Tap the Shape, Anywhere You LikeÕ: Shape
Skeletons in Human Vision Revealed by an Exceedingly Simple MeasureÓ, Psychological Science, Volume 25, Number
2, 2014, pp 377Ð386.
http://www.cs.toronto.edu/~sven/2523/Papers/FirestoneScholl.pdf
7. Symmetry as a Basis for 3-D Shape Perception
D.
Marr and H.K. Nishihara, ÒRepresentation and Recognition of the Spatial
Organization of Three Dimensional ShapesÓ, Proceedings
of Royal Society of London B, Volume 200, 1978, pp 269-294.
http://www.cs.toronto.edu/~sven/2523/Papers/MarrNishihara1978.pdf
R. Brooks, ÒSymbolic Reasoning Among 3-D Models
and 2-D Images", Artificial
Intelligence Journal, Volume 17, Numbers 1-3, 1981, pp 285-348.
http://www.cs.toronto.edu/~sven/2523/Papers/BrooksAIJ81.pdf
Supplemental:
T. Binford, ÒVisual Perception by ComputerÓ, Proceedings, IEEE
Conference on Systems and Control, Miami, FL, 1971.
http://www.cs.toronto.edu/~sven/2523/Papers/binford.pdf
G. Agin and T. Binford, ÒComputer
Description of Curved ObjectsÓ, IEEE
Transactions on Computers, Volume 25, Number 4, 1976, pp 439-449.
http://www.cs.toronto.edu/~sven/2523/Papers/AginBinford76.pdf
R. Nevatia and T. Binford,
ÒDescription and Recognition of Curved ObjectsÓ, Artificial Intelligence, Volume 8, 1977, pp 77-98.
http://www.cs.toronto.edu/~sven/2523/Papers/nevatia.pdf
M. Ovsjanikov, J. Sun, and L. Guibas,
ÒGlobal Intrinsic Symmetries of ShapesÓ, Eurographics
Symposium on Geometry Processing 2008, Volume 27, Number 5, 2008.
http://www.cs.toronto.edu/~sven/2523/Papers/ovs-symm.pdf
8. Qualitative Shape
Perception in 2-D
W.
Richards and D. Hoffman, ÒCodon constraints on closed 2D shapesÓ, Computer
Vision, Graphics and Image Processing, Volume 31, Number 3, 1985, pp 265-281.
http://www.cs.toronto.edu/~sven/2523/Papers/RichardsHoffman1985.pdf
K.
Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker, ÒShock Graphs and Shape MatchingÓ, International
Journal of Computer Vision, Volume 30, 1999, pp 1-24.
http://www.cs.toronto.edu/~sven/2523/Papers/ShockGraph.pdf
Supplemental:
S. Belongie, J. Malik and J. Puzicha,
``Shape Matching and Object Recognition Using Shape Contexts, IEEE Transactions on Pattern Analysis and
Machine Intelligence, Volume 24, Number 4, pp 509-522, 2002.
http://www.cs.toronto.edu/~sven/2523/Papers/belongie.pdf
9. Qualitative Shape Perception in 3-D
I. Biederman, ÒRecognition-by-Components: A Theory of Human
Image UnderstandingÓ, Psychological
Review, Volume 94, 1987, pp 115-147.
http://www.cs.toronto.edu/~sven/2523/Papers/biederman.pdf
S. Tulsiani, H. Su, L. Guibas, A. Efros, and J. Malik, ÒLearning Shape Abstractions by
Assembling Volumetric PrimitivesÓ, Proceedings, IEEE Conference in Computer
Vision and Pattern Recognition, 2017.
http://www.cs.toronto.edu/~sven/2523/Papers/Tulsiani2017.pdf
Supplemental:
A. Pentland, ÒPerceptual Organization and the Representation
of Natural FormÓ, Artificial Intelligence,
Volume 28, Number 2, 1986, pp 293-331.
http://www.cs.toronto.edu/~sven/2523/Papers/pentland.pdf
A. Gupta, A. Efros, and
M. Hebert, ÒBlocks World Revisited: Image Understanding using Qualitative Geometry
and MechanicsÓ, European Conference on Computer Vision (ECCV), September, 2010.
http://www.cs.toronto.edu/~sven/2523/Papers/Gupta2010.pdf
10. Deformable Models of Shape in 2-D
K. Denisova, J.
Feldman, X. Su, and M. Singh, ÒInvestigating shape representation using
sensitivity to part- and axis-based transformationsÓ, Vision Research, Volume 126, 2016, pp 347-361.
http://www.cs.toronto.edu/~sven/2523/Papers/Denisova2016.pdf
P. Felzenszwalb, ÒRepresentation and Detection of Deformable
ShapesÓ, IEEE Transactions on Pattern
Analysis and Machine Intelligence, Volume: 27, Number 2, 2005, pp 208-220.
http://www.cs.toronto.edu/~sven/2523/Papers/Felzenszwalb2005.pdf
Supplemental:
S. Sclaroff and A. Pentland, ÒModal
Matching for Correspondence and RecognitionÓ, IEEE Transactions on Pattern Analysis and Machine Intelligence,
Volume 17, Number 6, 1995, pp 545-561.
http://www.cs.toronto.edu/~sven/2523/Papers/sclaroff.pdf
R. Basri, L. Costa, D. Geiger, and D. Jacobs, ÒDetermining the
Similarity of Deformable ShapesÓ, Vision
Research, Volume 38, 1998, pp 2365-2385.
http://www.cs.toronto.edu/~sven/2523/Papers/basri.pdf
11. Deformable Models of Shape in 3-D
P. Sprote
and R. Fleming, ÒBent out of shape: The visual inference of non-rigid shape transformations
applied to objectsÓ, Vision Research,
Volume 126, 2016, pp 330-346.
http://www.cs.toronto.edu/~sven/2523/Papers/SproteFleming2016.pdf
S.
Dickinson and D. Metaxas, ÒIntegrating Qualitative and Quantitative Shape
RecoveryÓ, International Journal of
Computer Vision, Volume 13, Number 3, 1994, pp 1-20. http://www.cs.toronto.edu/~sven/2523/Papers/DickinsonMetaxas1994.pdf
Supplemental:
Y. Chen, T.-K. Kim, and R. Cipolla, ÒInferring 3D Shapes and Deformations from Single
ViewsÓ, Proceedings, European Conferene om Computer
Vision, 2010.
http://www.cs.toronto.edu/~sven/2523/Papers/Chen2010.pdf
A. Kanazawa, S. Kovalsky, R. Basri, and D. Jacobs,
ÒLearning 3D Deformation of Animals from 2D ImagesÓ, EUROGRAPHICS 2016, Volume
35, Number 2, 2016.
http://www.cs.toronto.edu/~sven/2523/Papers/Kanazawa2016.pdf
Q. Tan, L. Gao, Y.-K. Lai, J. Yang, and S. Xia, ÒMesh-based Autoencoders
for Localized Deformation Component AnalysisÓ.
https://arxiv.org/abs/1709.04304
12. Architectures for Shape Perception
M. and T. Poggio, ÒHierarchical models of object recognition in
cortexÓ, Nature Neuroscience, Volume
2, Number 11, 1999, pp 1019-1025.
http://www.cs.toronto.edu/~sven/2523/Papers/RiesenhuberPoggio1999.pdf
W. Shen, K. Zhao, Y. Jiang, Y. Wang, X. Bai
and A. Yuille, ÒDeepSkeleton:
Learning Multi-task Scale-associated Deep Side Outputs
for Object Skeleton Extraction in Natural ImagesÓ, Proceedings, IEEE Conference
on Computer Vision and Pattern Recognition, 2016.
http://www.cs.toronto.edu/~sven/2523/Papers/DeepSkeleton.pdf
Supplemental:
H. Huang, E. Kalogerakis,
B. Marlin, ÒAnalysis and synthesis of 3D shape families via deep-learned
generative models of surfacesÓ, Eurographics
Symposium on Geometry Processing 2015, Volume 34, Number 5, 2015.
http://www.cs.toronto.edu/~sven/2523/Papers/Huang-AnalysisAndSynthesisOf3DShapeFamilies.pdf
J. Wu, C. Zhang, T. Xue,
W. T. Freeman, and J. B. Tenenbaum, ÒLearning a
Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial
ModelingÓ, Proceedings, NIPS, 2016.
http://www.cs.toronto.edu/~sven/2523/Papers/Wu2016.pdf
C. Nash and C. K. I. Williams, ÒThe shape variational autoencoder: A deep
generative model of part-segmented 3D objectsÓ, Eurographics
Symposium on Geometry Processing 2017, Volume 36, Number 5, 2017.
http://www.cs.toronto.edu/~sven/2523/Papers/Nash-TheShapeVariationalAutoencoder.pdf