Non-local sparse models for image restoration
We propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. On the other hand, explicitly exploiting the sel...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2010
|
| _version_ | 1824458932309983232 |
|---|---|
| author | Mairal, J Bach, F Ponce, J Sapiro, G Zisserman, A |
| author_facet | Mairal, J Bach, F Ponce, J Sapiro, G Zisserman, A |
| author_sort | Mairal, J |
| collection | OXFORD |
| description | We propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. On the other hand, explicitly exploiting the self-similarities of natural images has led to the successful non-local means approach to image restoration. We propose simultaneous sparse coding as a framework for combining these two approaches in a natural manner. This is achieved by jointly decomposing groups of similar signals on subsets of the learned dictionary. Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost. |
| first_indexed | 2025-02-19T04:33:45Z |
| format | Conference item |
| id | oxford-uuid:cbb65689-27c6-4fd2-ba84-e953e61c0510 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:33:45Z |
| publishDate | 2010 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:cbb65689-27c6-4fd2-ba84-e953e61c05102025-01-15T12:44:57ZNon-local sparse models for image restorationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:cbb65689-27c6-4fd2-ba84-e953e61c0510EnglishSymplectic ElementsIEEE2010Mairal, JBach, FPonce, JSapiro, GZisserman, AWe propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. On the other hand, explicitly exploiting the self-similarities of natural images has led to the successful non-local means approach to image restoration. We propose simultaneous sparse coding as a framework for combining these two approaches in a natural manner. This is achieved by jointly decomposing groups of similar signals on subsets of the learned dictionary. Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost. |
| spellingShingle | Mairal, J Bach, F Ponce, J Sapiro, G Zisserman, A Non-local sparse models for image restoration |
| title | Non-local sparse models for image restoration |
| title_full | Non-local sparse models for image restoration |
| title_fullStr | Non-local sparse models for image restoration |
| title_full_unstemmed | Non-local sparse models for image restoration |
| title_short | Non-local sparse models for image restoration |
| title_sort | non local sparse models for image restoration |
| work_keys_str_mv | AT mairalj nonlocalsparsemodelsforimagerestoration AT bachf nonlocalsparsemodelsforimagerestoration AT poncej nonlocalsparsemodelsforimagerestoration AT sapirog nonlocalsparsemodelsforimagerestoration AT zissermana nonlocalsparsemodelsforimagerestoration |