Further Evidence Against the Recovery Theory of Vision
The problem of three-dimensional vision is generally formulated as the problem of recovering the three-dimensional scene that caused the image. We have previously presented a certain line-drawing and shown that it has the following property: the three-dimensional object we see when we look at this...
| 主要作者: | |
|---|---|
| 格式: | Working Paper |
| 语言: | en_US |
| 出版: |
MIT Artificial Intelligence Laboratory
2008
|
| 在线阅读: | http://hdl.handle.net/1721.1/41493 |
| _version_ | 1826216578543255552 |
|---|---|
| author | Marill, Thomas |
| author_facet | Marill, Thomas |
| author_sort | Marill, Thomas |
| collection | MIT |
| description | The problem of three-dimensional vision is generally formulated as the problem of recovering the three-dimensional scene that caused the image.
We have previously presented a certain line-drawing and shown that it has the following property: the three-dimensional object we see when we look at this line-drawing does not have the line-drawing as its image. It would therefore be impossible for the seen object to be the cause of the image. Such an occurrence constitutes a counterexample to the theory that vision recovers the scene that caused the image.
Here we show that such a counterexample is not an isolated case, but is the rule rather than the exception. Thus, as a general matter, the three-dimensional scenes we see when we look at line-drawings do not have these drawings as their image. This represents further evidence against the recovery theory. |
| first_indexed | 2024-09-23T16:49:48Z |
| format | Working Paper |
| id | mit-1721.1/41493 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:49:48Z |
| publishDate | 2008 |
| publisher | MIT Artificial Intelligence Laboratory |
| record_format | dspace |
| spelling | mit-1721.1/414932019-04-10T23:12:23Z Further Evidence Against the Recovery Theory of Vision Marill, Thomas The problem of three-dimensional vision is generally formulated as the problem of recovering the three-dimensional scene that caused the image. We have previously presented a certain line-drawing and shown that it has the following property: the three-dimensional object we see when we look at this line-drawing does not have the line-drawing as its image. It would therefore be impossible for the seen object to be the cause of the image. Such an occurrence constitutes a counterexample to the theory that vision recovers the scene that caused the image. Here we show that such a counterexample is not an isolated case, but is the rule rather than the exception. Thus, as a general matter, the three-dimensional scenes we see when we look at line-drawings do not have these drawings as their image. This represents further evidence against the recovery theory. MIT Artificial Intelligence Laboratory 2008-04-28T14:58:08Z 2008-04-28T14:58:08Z 1989-02 Working Paper http://hdl.handle.net/1721.1/41493 en_US MIT Artificial Intelligence Laboratory Working Papers, WP-320 application/pdf MIT Artificial Intelligence Laboratory |
| spellingShingle | Marill, Thomas Further Evidence Against the Recovery Theory of Vision |
| title | Further Evidence Against the Recovery Theory of Vision |
| title_full | Further Evidence Against the Recovery Theory of Vision |
| title_fullStr | Further Evidence Against the Recovery Theory of Vision |
| title_full_unstemmed | Further Evidence Against the Recovery Theory of Vision |
| title_short | Further Evidence Against the Recovery Theory of Vision |
| title_sort | further evidence against the recovery theory of vision |
| url | http://hdl.handle.net/1721.1/41493 |
| work_keys_str_mv | AT marillthomas furtherevidenceagainsttherecoverytheoryofvision |