Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture
We identify and study two types of “accidental” images that can be formed in scenes. The first is an accidental pinhole camera image. These images are often mistaken for shadows, but can reveal structures outside a room, or the unseen shape of the light aperture into the room. The second class of ac...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/90953 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1826216381214883840 |
|---|---|
| author | Torralba, Antonio Freeman, William T. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Torralba, Antonio Freeman, William T. |
| author_sort | Torralba, Antonio |
| collection | MIT |
| description | We identify and study two types of “accidental” images that can be formed in scenes. The first is an accidental pinhole camera image. These images are often mistaken for shadows, but can reveal structures outside a room, or the unseen shape of the light aperture into the room. The second class of accidental images are “inverse” pinhole camera images, formed by subtracting an image with a small occluder present from a reference image without the occluder. The reference image can be an earlier frame of a video sequence. Both types of accidental images happen in a variety of different situations (an indoor scene illuminated by natural light, a street with a person walking under the shadow of a building, etc.). Accidental cameras can reveal information about the scene outside the image, the lighting conditions, or the aperture by which light enters the scene. |
| first_indexed | 2024-09-23T16:46:45Z |
| format | Article |
| id | mit-1721.1/90953 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:46:45Z |
| publishDate | 2014 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/909532022-09-29T21:25:17Z Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture Torralba, Antonio Freeman, William T. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Torralba, Antonio Freeman, William T. We identify and study two types of “accidental” images that can be formed in scenes. The first is an accidental pinhole camera image. These images are often mistaken for shadows, but can reveal structures outside a room, or the unseen shape of the light aperture into the room. The second class of accidental images are “inverse” pinhole camera images, formed by subtracting an image with a small occluder present from a reference image without the occluder. The reference image can be an earlier frame of a video sequence. Both types of accidental images happen in a variety of different situations (an indoor scene illuminated by natural light, a street with a person walking under the shadow of a building, etc.). Accidental cameras can reveal information about the scene outside the image, the lighting conditions, or the aperture by which light enters the scene. National Science Foundation (U.S.) (NSF Career Award No. 0747120) National Science Foundation (U.S.) (NSF CGV-1111415) National Science Foundation (U.S.) (NSF CGV 0964004) 2014-10-15T20:15:19Z 2014-10-15T20:15:19Z 2012-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-1228-8 978-1-4673-1226-4 978-1-4673-1227-1 1063-6919 INSPEC Accession Number: 12884784 http://hdl.handle.net/1721.1/90953 Torralba, A., and W. T. Freeman. “Accidental Pinhole and Pinspeck Cameras: Revealing the Scene Outside the Picture.” 2012 IEEE Conference on Computer Vision and Pattern Recognition (June 2012), 16-21 June 2012, Providence, RI. IEEE, p.374-381. https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPR.2012.6247698 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Torralba, Antonio Freeman, William T. Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title | Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title_full | Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title_fullStr | Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title_full_unstemmed | Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title_short | Accidental pinhole and pinspeck cameras: Revealing the scene outside the picture |
| title_sort | accidental pinhole and pinspeck cameras revealing the scene outside the picture |
| url | http://hdl.handle.net/1721.1/90953 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT torralbaantonio accidentalpinholeandpinspeckcamerasrevealingthesceneoutsidethepicture AT freemanwilliamt accidentalpinholeandpinspeckcamerasrevealingthesceneoutsidethepicture |