Learning to Perceive Transparency from the Statistics of Natural Scenes

Anat Levin; Assaf Zomet; Yair Weiss

Learning to Perceive Transparency from the Statistics of Natural Scenes

Anat Levin, Assaf Zomet, Yair Weiss

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

46 Scopus citations

Abstract

Certain simple images are known to trigger a percept of transparency: the input image I is perceived as the sum of two images I(x, y) = I₁(x, y) + I₂(x, y). This percept is puzzling. First, why do we choose the “more complicated” description with two images rather than the “simpler” explanation I(x, y) = I₁(x, y) + 0 ? Second, given the infinite number of ways to express I as a sum of two images, how do we compute the “best” decomposition ? Here we suggest that transparency is the rational percept of a system that is adapted to the statistics of natural scenes. We present a probabilistic model of images based on the qualitative statistics of derivative filters and “corner detectors” in natural scenes and use this model to find the most probable decomposition of a novel image. The optimization is performed using loopy belief propagation. We show that our model computes perceptually “correct” decompositions on synthetic images and discuss its application to real images.

Original language	English
Title of host publication	NIPS 2002
Subtitle of host publication	Proceedings of the 15th International Conference on Neural Information Processing Systems
Editors	Suzanna Becker, Sebastian Thrun, Klaus Obermayer
Publisher	MIT Press Journals
Pages	1247-1254
Number of pages	8
ISBN (Electronic)	0262025507, 9780262025508
State	Published - 2002
Event	15th International Conference on Neural Information Processing Systems, NIPS 2002 - Vancouver, Canada Duration: 9 Dec 2002 → 14 Dec 2002

Publication series

Name	NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

Conference

Conference	15th International Conference on Neural Information Processing Systems, NIPS 2002
Country/Territory	Canada
City	Vancouver
Period	9/12/02 → 14/12/02

Bibliographical note

Publisher Copyright:
© NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. All rights reserved.

Cite this

Levin, A., Zomet, A., & Weiss, Y. (2002). Learning to Perceive Transparency from the Statistics of Natural Scenes. In S. Becker, S. Thrun, & K. Obermayer (Eds.), NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems (pp. 1247-1254). (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems). MIT Press Journals.

Levin, Anat ; Zomet, Assaf ; Weiss, Yair. / Learning to Perceive Transparency from the Statistics of Natural Scenes. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. editor / Suzanna Becker ; Sebastian Thrun ; Klaus Obermayer. MIT Press Journals, 2002. pp. 1247-1254 (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

@inproceedings{2d91c546d46544439e3b60947e088534,

title = "Learning to Perceive Transparency from the Statistics of Natural Scenes",

abstract = "Certain simple images are known to trigger a percept of transparency: the input image I is perceived as the sum of two images I(x, y) = I1(x, y) + I2(x, y). This percept is puzzling. First, why do we choose the “more complicated” description with two images rather than the “simpler” explanation I(x, y) = I1(x, y) + 0 ? Second, given the infinite number of ways to express I as a sum of two images, how do we compute the “best” decomposition ? Here we suggest that transparency is the rational percept of a system that is adapted to the statistics of natural scenes. We present a probabilistic model of images based on the qualitative statistics of derivative filters and “corner detectors” in natural scenes and use this model to find the most probable decomposition of a novel image. The optimization is performed using loopy belief propagation. We show that our model computes perceptually “correct” decompositions on synthetic images and discuss its application to real images.",

author = "Anat Levin and Assaf Zomet and Yair Weiss",

note = "Publisher Copyright: {\textcopyright} NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. All rights reserved.; 15th International Conference on Neural Information Processing Systems, NIPS 2002 ; Conference date: 09-12-2002 Through 14-12-2002",

year = "2002",

language = "אנגלית",

series = "NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems",

publisher = "MIT Press Journals",

pages = "1247--1254",

editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer",

booktitle = "NIPS 2002",

address = "ארצות הברית",

}

Levin, A, Zomet, A & Weiss, Y 2002, Learning to Perceive Transparency from the Statistics of Natural Scenes. in S Becker, S Thrun & K Obermayer (eds), NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems, MIT Press Journals, pp. 1247-1254, 15th International Conference on Neural Information Processing Systems, NIPS 2002, Vancouver, Canada, 9/12/02.

Learning to Perceive Transparency from the Statistics of Natural Scenes. / Levin, Anat; Zomet, Assaf; Weiss, Yair.
NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. ed. / Suzanna Becker; Sebastian Thrun; Klaus Obermayer. MIT Press Journals, 2002. p. 1247-1254 (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning to Perceive Transparency from the Statistics of Natural Scenes

AU - Levin, Anat

AU - Zomet, Assaf

AU - Weiss, Yair

PY - 2002

Y1 - 2002

N2 - Certain simple images are known to trigger a percept of transparency: the input image I is perceived as the sum of two images I(x, y) = I1(x, y) + I2(x, y). This percept is puzzling. First, why do we choose the “more complicated” description with two images rather than the “simpler” explanation I(x, y) = I1(x, y) + 0 ? Second, given the infinite number of ways to express I as a sum of two images, how do we compute the “best” decomposition ? Here we suggest that transparency is the rational percept of a system that is adapted to the statistics of natural scenes. We present a probabilistic model of images based on the qualitative statistics of derivative filters and “corner detectors” in natural scenes and use this model to find the most probable decomposition of a novel image. The optimization is performed using loopy belief propagation. We show that our model computes perceptually “correct” decompositions on synthetic images and discuss its application to real images.

AB - Certain simple images are known to trigger a percept of transparency: the input image I is perceived as the sum of two images I(x, y) = I1(x, y) + I2(x, y). This percept is puzzling. First, why do we choose the “more complicated” description with two images rather than the “simpler” explanation I(x, y) = I1(x, y) + 0 ? Second, given the infinite number of ways to express I as a sum of two images, how do we compute the “best” decomposition ? Here we suggest that transparency is the rational percept of a system that is adapted to the statistics of natural scenes. We present a probabilistic model of images based on the qualitative statistics of derivative filters and “corner detectors” in natural scenes and use this model to find the most probable decomposition of a novel image. The optimization is performed using loopy belief propagation. We show that our model computes perceptually “correct” decompositions on synthetic images and discuss its application to real images.

UR - http://www.scopus.com/inward/record.url?scp=85133208486&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85133208486

T3 - NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

SP - 1247

EP - 1254

BT - NIPS 2002

A2 - Becker, Suzanna

A2 - Thrun, Sebastian

A2 - Obermayer, Klaus

PB - MIT Press Journals

T2 - 15th International Conference on Neural Information Processing Systems, NIPS 2002

Y2 - 9 December 2002 through 14 December 2002

ER -

Levin A, Zomet A, Weiss Y. Learning to Perceive Transparency from the Statistics of Natural Scenes. In Becker S, Thrun S, Obermayer K, editors, NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. MIT Press Journals. 2002. p. 1247-1254. (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

Learning to Perceive Transparency from the Statistics of Natural Scenes

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this