Bayesian inference of form and shape.

The ability to visually perceive two-dimensional (2D) form and three-dimensional (3D) shape is one of our most fundamental faculties. This ability relies on considerable prior knowledge about the way edge elements in an image are likely to be connected together into a contour as well as the way these 2D contours relate to 3D shapes. The interaction of prior knowledge with image information is well modeled within a Bayesian framework. We review here the experimental evidence of shape perception seen as a Bayesian inference problem.

[1]  Marco Bertamini,et al.  The shape of holes , 2003, Cognition.

[2]  J. Feldman,et al.  Information along contours and object boundaries. , 2005, Psychological review.

[3]  D C Knill,et al.  Perception of surface contours and surface shape: from computation to psychophysics. , 1992, Journal of the Optical Society of America. A, Optics and image science.

[4]  P. Tse.  A contour propagation approach to surface filling-in and volume formation. , 2001, Psychological review.

[5]  Pascal Mamassian,et al.  Impossible Shadows and the Shadow Correspondence Problem , 2004, Perception.

[6]  P. Kellman,et al.  A theory of visual interpolation in object perception , 1991, Cognitive Psychology.

[7]  Qasim Zaidi,et al.  Three-dimensional shape from non-homogeneous textures: carved and stretched surfaces. , 2004, Journal of vision.

[8]  Scott O. Murray,et al.  Perceptual grouping and the interactions between visual cortical areas , 2004, Neural Networks.

[9]  Michael S. Landy,et al.  Interpolating sampled contours in 3-D: analyses of variability and bias , 2002, Vision Research.

[10]  Pascal Mamassian,et al.  Observer biases in the 3D interpretation of line drawings , 1998, Vision Research.

[11]  Dale Purves,et al.  Natural-scene geometry predicts the perception of angles and line orientation. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Jeffrey S. Perry,et al.  Edge co-occurrence in natural images predicts contour grouping performance , 2001, Vision Research.

[13]  Achille C. Varzi,et al.  Holes and Other Superficialities , 1994 .

[14]  P. Mamassian,et al.  Prior knowledge on the illumination position , 2001, Cognition.

[15]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[16]  David J. Field,et al.  Contour integration by the human visual system: Evidence for a local “association field” , 1993, Vision Research.

[17]  J. Elder,et al.  Ecological statistics of Gestalt laws for the perceptual organization of contours. , 2002, Journal of vision.

[18]  H. Ross,et al.  Information Concentration along the Boundary Contours of Naturally Shaped Solid Objects , 2001, Perception.

[19]  A. Yuille,et al.  Object perception as Bayesian inference. , 2004, Annual review of psychology.

[20]  Jacob feldman,et al.  Bayesian contour integration , 2001, Perception & psychophysics.

[21]  R. Basri,et al.  The role of convexity in perceptual completion: beyond good continuation , 1999, Vision Research.

[22]  M. Kubovy,et al.  Grouping by Proximity and Multistability in Dot Lattices: A Quantitative Gestalt Theory , 1995 .

[23]  J J Koenderink,et al.  What Does the Occluding Contour Tell Us about Solid Shape? , 1984, Perception.

[24]  Rajesh P. N. Rao,et al.  Probabilistic Models of the Brain: Perception and Neural Function , 2002 .

[25]  M. Landy,et al.  Bayesian Modelling of Visual Perception , 2002 .

[26]  Nick Chater,et al.  Reconciling simplicity and likelihood principles in perceptual organization. , 1996, Psychological review.