A sampled texture prior for image super-resolution
Super-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical approaches try to reconstruct a high-resolution image using the sub-pixel displacements of several low- resolution image...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
MIT Press
2004
|
| _version_ | 1826317315192389632 |
|---|---|
| author | Pickup, LC Roberts, SJ Zisserman, A |
| author_facet | Pickup, LC Roberts, SJ Zisserman, A |
| author_sort | Pickup, LC |
| collection | OXFORD |
| description | Super-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical approaches try to reconstruct a high-resolution image using the sub-pixel displacements of several low- resolution images, usually regularized by a generic smoothness prior over the high-resolution image space. Other methods use training data to learn low-to-high-resolution matches, and have been highly successful even in the single-input-image case. Here we present a domain-specific im- age prior in the form of a p.d.f. based upon sampled images, and show that for certain types of super-resolution problems, this sample-based prior gives a significant improvement over other common multiple-image super-resolution techniques. |
| first_indexed | 2024-03-07T01:17:45Z |
| format | Conference item |
| id | oxford-uuid:8f48524f-51cf-479f-97c1-9962b6f8a35e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:36:32Z |
| publishDate | 2004 |
| publisher | MIT Press |
| record_format | dspace |
| spelling | oxford-uuid:8f48524f-51cf-479f-97c1-9962b6f8a35e2025-02-04T15:43:14ZA sampled texture prior for image super-resolutionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:8f48524f-51cf-479f-97c1-9962b6f8a35eEnglishSymplectic Elements at OxfordMIT Press2004Pickup, LCRoberts, SJZisserman, ASuper-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical approaches try to reconstruct a high-resolution image using the sub-pixel displacements of several low- resolution images, usually regularized by a generic smoothness prior over the high-resolution image space. Other methods use training data to learn low-to-high-resolution matches, and have been highly successful even in the single-input-image case. Here we present a domain-specific im- age prior in the form of a p.d.f. based upon sampled images, and show that for certain types of super-resolution problems, this sample-based prior gives a significant improvement over other common multiple-image super-resolution techniques. |
| spellingShingle | Pickup, LC Roberts, SJ Zisserman, A A sampled texture prior for image super-resolution |
| title | A sampled texture prior for image super-resolution |
| title_full | A sampled texture prior for image super-resolution |
| title_fullStr | A sampled texture prior for image super-resolution |
| title_full_unstemmed | A sampled texture prior for image super-resolution |
| title_short | A sampled texture prior for image super-resolution |
| title_sort | sampled texture prior for image super resolution |
| work_keys_str_mv | AT pickuplc asampledtexturepriorforimagesuperresolution AT robertssj asampledtexturepriorforimagesuperresolution AT zissermana asampledtexturepriorforimagesuperresolution AT pickuplc sampledtexturepriorforimagesuperresolution AT robertssj sampledtexturepriorforimagesuperresolution AT zissermana sampledtexturepriorforimagesuperresolution |