Ground truth dataset and baseline evaluations for intrinsic image algorithms
The intrinsic image decomposition aims to retrieve “intrinsic” properties of an image, such as shading and reflectance. To make it possible to quantitatively compare different approaches to this problem in realistic settings, we present a ground-truth dataset of intrinsic image decompositions for a...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/59363 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-2222-6775 |
| _version_ | 1826210425625116672 |
|---|---|
| author | Grosse, Roger Baker Johnson, Micah K. Adelson, Edward H. Freeman, William T. |
| author2 | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
| author_facet | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Grosse, Roger Baker Johnson, Micah K. Adelson, Edward H. Freeman, William T. |
| author_sort | Grosse, Roger Baker |
| collection | MIT |
| description | The intrinsic image decomposition aims to retrieve “intrinsic” properties of an image, such as shading and reflectance. To make it possible to quantitatively compare different approaches to this problem in realistic settings, we present a ground-truth dataset of intrinsic image decompositions for a variety of real-world objects. For each object, we separate an image of it into three components: Lambertian shading, reflectance, and specularities. We use our dataset to quantitatively compare several existing algorithms; we hope that this dataset will serve as a means for evaluating future work on intrinsic images. |
| first_indexed | 2024-09-23T14:49:41Z |
| format | Article |
| id | mit-1721.1/59363 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:49:41Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/593632022-10-01T22:43:31Z Ground truth dataset and baseline evaluations for intrinsic image algorithms Grosse, Roger Baker Johnson, Micah K. Adelson, Edward H. Freeman, William T. Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Freeman, William T. Grosse, Roger Baker Johnson, Micah K. Adelson, Edward H. Freeman, William T. The intrinsic image decomposition aims to retrieve “intrinsic” properties of an image, such as shading and reflectance. To make it possible to quantitatively compare different approaches to this problem in realistic settings, we present a ground-truth dataset of intrinsic image decompositions for a variety of real-world objects. For each object, we separate an image of it into three components: Lambertian shading, reflectance, and specularities. We use our dataset to quantitatively compare several existing algorithms; we hope that this dataset will serve as a means for evaluating future work on intrinsic images. United States. National Geospatial-Intelligence Agency National Science Foundation (U.S.) (grant 0739255) United States. National Geospatial-Intelligence Agency (NEGI- 1582-04-0004) Multidisciplinary University Research Initiative (MURI) (Grant N00014-06-1-0734) 2010-10-15T14:44:07Z 2010-10-15T14:44:07Z 2010-05 2009-10 Article http://purl.org/eprint/type/JournalArticle 978-1-4244-4420-5 1550-5499 INSPEC Accession Number: 11367860 http://hdl.handle.net/1721.1/59363 Grosse, R. et al. “Ground truth dataset and baseline evaluations for intrinsic image algorithms.” Computer Vision, 2009 IEEE 12th International Conference on. 2009. 2335-2342. © Copyright 2009 IEEE https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-2222-6775 en_US http://dx.doi.org/10.1109/ICCV.2009.5459428 Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Grosse, Roger Baker Johnson, Micah K. Adelson, Edward H. Freeman, William T. Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title_full | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title_fullStr | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title_full_unstemmed | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title_short | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| title_sort | ground truth dataset and baseline evaluations for intrinsic image algorithms |
| url | http://hdl.handle.net/1721.1/59363 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-2222-6775 |
| work_keys_str_mv | AT grosserogerbaker groundtruthdatasetandbaselineevaluationsforintrinsicimagealgorithms AT johnsonmicahk groundtruthdatasetandbaselineevaluationsforintrinsicimagealgorithms AT adelsonedwardh groundtruthdatasetandbaselineevaluationsforintrinsicimagealgorithms AT freemanwilliamt groundtruthdatasetandbaselineevaluationsforintrinsicimagealgorithms |