Abstract
A central goal for visual perception is the recovery of the three-dimensional structure of the surfaces depicted in an image. Crucial information about three-dimensional structure is provided by the spatial distribution of surface markings, particularly for static monocular views: projection distorts texture geometry in a manner tha depends systematically on surface shape and orientation. To isolate and measure this projective distortion in an image is to recover the three dimensional structure of the textured surface. For natural textures, we show that the uniform density assumption (texels are uniformly distributed) is enough to recover the orientation of a single textured plane in view, under perspective projection. Furthermore, when the texels cannot be found, the edges of the image are enough to determine shape, under a more general assumption, that the sum of the lengths of the contours on the world plane is about the same everywhere. Finally, several experimental results for synthetic and natural images are presented.
Similar content being viewed by others
References
Aloimonos J, Swain M (1987) Paraperspective projection: between orthography and perspective (submitted for publication)
Bajcsy R, Liebermann L (1976) Texture gradients as a depth cue. Comp Graph Image Process 5:52–76
Ballard D (1984) Parameter networks. Arti Intell 22:235–267
Bandopadhyay A (1984) Interest points, disparities and correspondence. Proceedings of the IEEE Workshop on Computer Vision: Representation and Control. Annapolis M, pp 78–82
Blonstein D, Ahuja N (1987) Representation and interpretation of texture: an integrated approach. Technical Report 87-2226, Coordinated Science Laboratory, University of Illinois at Urbana Champaign
Cany J (1984) Master's Thesis. Ariticial Intelligence Laboratory, Massachusetts Institute of Technology, Mass
Feldman J (1985) Four frames suffice: a provisional model of vision and space. Behav Brain Sci June (1985)
Gibson JJ (1950) The perception of the visual world. Houghton Mifflin, Boston
Horn BKP (1985) Robot vision. McGraw-Hill, New York
Ikeuchi K (1984) Shape from regular patterns. Artif Intell 22:49–75
Kanade T (1979) Recovery of the three dimensional shape of an object from a single view CMU-CS-79-153. Department of Computer Science. Carnegie-Mellon University
Kanatani K (1984) Detection of surface orientation and motion from texture by a stereological technique. Artif Intell 23:213–237
Kender J (1980) Ph.D. thesis. Carnegie-Mellon University
Marr D, Hildreth E (1979) Theory of edge detection. Proc R Soc Lond B 207:301–328
Nalwa V (1987) Ph.D. Thesis. Department of Computer Science, Stanford University
Ohta Y, Maenobu K, Sakai T (1981) Obtaining surface orientation from texels under perspective projection. Proceedings of the 7th IJCAI, Vancouver, Canada, pp 746–751
Shulman D, Aloimonos J (1987) A linear theory of boundary preserving regularization. Technical Report Computer Vision Laboratory, Center for Automation Research. University of Maryland
Stevens KA (1979) Surface perception from local analysis of texture and contour. Ph.D. thesis, Technical Report TR 512. MIT, Cambridge, Mass
Witkin A (1981) Recovering surface shape and orientations from texture. Artif Intell 17:17–45
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Aloimonos, J. Shape from texture. Biol. Cybern. 58, 345–360 (1988). https://doi.org/10.1007/BF00363944
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00363944