MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Artificial Intelligence Lab Publications
  • AI Memos (1959 - 2004)
  • View Item
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Artificial Intelligence Lab Publications
  • AI Memos (1959 - 2004)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Recognition of Surface Reflectance Properties from a Single Image under Unknown Real-World Illumination

Author(s)
Dror, Ron O.; Edward H. Adelson,; Willsky, Alan S.
Thumbnail
DownloadAIM-2001-033.ps (5.685Mb)
Additional downloads
AIM-2001-033.pdf (811.7Kb)
Metadata
Show full item record
Abstract
This paper describes a machine vision system that classifies reflectance properties of surfaces such as metal, plastic, or paper, under unknown real-world illumination. We demonstrate performance of our algorithm for surfaces of arbitrary geometry. Reflectance estimation under arbitrary omnidirectional illumination proves highly underconstrained. Our reflectance estimation algorithm succeeds by learning relationships between surface reflectance and certain statistics computed from an observed image, which depend on statistical regularities in the spatial structure of real-world illumination. Although the algorithm assumes known geometry, its statistical nature makes it robust to inaccurate geometry estimates.
Date issued
2001-10-21
URI
http://hdl.handle.net/1721.1/6664
Other identifiers
AIM-2001-033
Series/Report no.
AIM-2001-033
Keywords
AI, illumination, reflectance, computer vision, geometry, natural image statistics

Collections
  • AI Memos (1959 - 2004)

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.