Probabilistic Solution of Ill-Posed Problems in Computational Vision
We formulate several problems in early vision as inverse problems. Among the solution methods we review standard regularization theory, discuss its limitations, and present new stochastic (in particular, Bayesian) techniques based on Markov Random Field models for their solution. We derive eff...
| Main Authors: | , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6449 |
| _version_ | 1826213237219131392 |
|---|---|
| author | Marroquin, J. Mitter, S. Poggio, T. |
| author_facet | Marroquin, J. Mitter, S. Poggio, T. |
| author_sort | Marroquin, J. |
| collection | MIT |
| description | We formulate several problems in early vision as inverse problems. Among the solution methods we review standard regularization theory, discuss its limitations, and present new stochastic (in particular, Bayesian) techniques based on Markov Random Field models for their solution. We derive efficient algorithms and describe parallel implementations on digital parallel SIMD architectures, as well as a new class of parallel hybrid computers that mix digital with analog components. |
| first_indexed | 2024-09-23T15:45:37Z |
| id | mit-1721.1/6449 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:45:37Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/64492019-04-11T04:54:44Z Probabilistic Solution of Ill-Posed Problems in Computational Vision Marroquin, J. Mitter, S. Poggio, T. We formulate several problems in early vision as inverse problems. Among the solution methods we review standard regularization theory, discuss its limitations, and present new stochastic (in particular, Bayesian) techniques based on Markov Random Field models for their solution. We derive efficient algorithms and describe parallel implementations on digital parallel SIMD architectures, as well as a new class of parallel hybrid computers that mix digital with analog components. 2004-10-04T14:56:53Z 2004-10-04T14:56:53Z 1987-03-01 AIM-897 http://hdl.handle.net/1721.1/6449 en_US AIM-897 5330897 bytes 2064608 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Marroquin, J. Mitter, S. Poggio, T. Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title | Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title_full | Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title_fullStr | Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title_full_unstemmed | Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title_short | Probabilistic Solution of Ill-Posed Problems in Computational Vision |
| title_sort | probabilistic solution of ill posed problems in computational vision |
| url | http://hdl.handle.net/1721.1/6449 |
| work_keys_str_mv | AT marroquinj probabilisticsolutionofillposedproblemsincomputationalvision AT mitters probabilisticsolutionofillposedproblemsincomputationalvision AT poggiot probabilisticsolutionofillposedproblemsincomputationalvision |