Surface Reflectance Estimation and Natural Illumination Statistics
Humans recognize optical reflectance properties of surfaces such as metal, plastic, or paper from a single image without knowledge of illumination. We develop a machine vision system to perform similar recognition tasks automatically. Reflectance estimation under unknown, arbitrary illumination prov...
| Main Authors: | , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6656 |
| _version_ | 1811087706135986176 |
|---|---|
| author | Dror, Ron O. Adelson, Edward H. Willsky, Alan S. |
| author_facet | Dror, Ron O. Adelson, Edward H. Willsky, Alan S. |
| author_sort | Dror, Ron O. |
| collection | MIT |
| description | Humans recognize optical reflectance properties of surfaces such as metal, plastic, or paper from a single image without knowledge of illumination. We develop a machine vision system to perform similar recognition tasks automatically. Reflectance estimation under unknown, arbitrary illumination proves highly underconstrained due to the variety of potential illumination distributions and surface reflectance properties. We have found that the spatial structure of real-world illumination possesses some of the statistical regularities observed in the natural image statistics literature. A human or computer vision system may be able to exploit this prior information to determine the most likely surface reflectance given an observed image. We develop an algorithm for reflectance classification under unknown real-world illumination, which learns relationships between surface reflectance and certain features (statistics) computed from a single observed image. We also develop an automatic feature selection method. |
| first_indexed | 2024-09-23T13:50:44Z |
| id | mit-1721.1/6656 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:50:44Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/66562019-04-11T02:52:42Z Surface Reflectance Estimation and Natural Illumination Statistics Dror, Ron O. Adelson, Edward H. Willsky, Alan S. AI reflectance lighting BRDF surface illumination statistics natural images Humans recognize optical reflectance properties of surfaces such as metal, plastic, or paper from a single image without knowledge of illumination. We develop a machine vision system to perform similar recognition tasks automatically. Reflectance estimation under unknown, arbitrary illumination proves highly underconstrained due to the variety of potential illumination distributions and surface reflectance properties. We have found that the spatial structure of real-world illumination possesses some of the statistical regularities observed in the natural image statistics literature. A human or computer vision system may be able to exploit this prior information to determine the most likely surface reflectance given an observed image. We develop an algorithm for reflectance classification under unknown real-world illumination, which learns relationships between surface reflectance and certain features (statistics) computed from a single observed image. We also develop an automatic feature selection method. 2004-10-08T20:36:32Z 2004-10-08T20:36:32Z 2001-09-01 AIM-2001-023 http://hdl.handle.net/1721.1/6656 en_US AIM-2001-023 22 p. 7750699 bytes 706071 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI reflectance lighting BRDF surface illumination statistics natural images Dror, Ron O. Adelson, Edward H. Willsky, Alan S. Surface Reflectance Estimation and Natural Illumination Statistics |
| title | Surface Reflectance Estimation and Natural Illumination Statistics |
| title_full | Surface Reflectance Estimation and Natural Illumination Statistics |
| title_fullStr | Surface Reflectance Estimation and Natural Illumination Statistics |
| title_full_unstemmed | Surface Reflectance Estimation and Natural Illumination Statistics |
| title_short | Surface Reflectance Estimation and Natural Illumination Statistics |
| title_sort | surface reflectance estimation and natural illumination statistics |
| topic | AI reflectance lighting BRDF surface illumination statistics natural images |
| url | http://hdl.handle.net/1721.1/6656 |
| work_keys_str_mv | AT drorrono surfacereflectanceestimationandnaturalilluminationstatistics AT adelsonedwardh surfacereflectanceestimationandnaturalilluminationstatistics AT willskyalans surfacereflectanceestimationandnaturalilluminationstatistics |