Compressive light field photography using overcomplete dictionaries and optimized projections
Light field photography has gained a significant research interest in the last two decades; today, commercial light field cameras are widely available. Nevertheless, most existing acquisition approaches either multiplex a low-resolution light field into a single 2D sensor image or require multiple p...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computing Machinery
2014
|
| Online Access: | http://hdl.handle.net/1721.1/92451 https://orcid.org/0000-0002-3254-3224 |
| _version_ | 1826207369888006144 |
|---|---|
| author | Marwah, Kshitij Wetzstein, Gordon Bando, Yosuke Raskar, Ramesh |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Marwah, Kshitij Wetzstein, Gordon Bando, Yosuke Raskar, Ramesh |
| author_sort | Marwah, Kshitij |
| collection | MIT |
| description | Light field photography has gained a significant research interest in the last two decades; today, commercial light field cameras are widely available. Nevertheless, most existing acquisition approaches either multiplex a low-resolution light field into a single 2D sensor image or require multiple photographs to be taken for acquiring a high-resolution light field. We propose a compressive light field camera architecture that allows for higher-resolution light fields to be recovered than previously possible from a single image. The proposed architecture comprises three key components: light field atoms as a sparse representation of natural light fields, an optical design that allows for capturing optimized 2D light field projections, and robust sparse reconstruction methods to recover a 4D light field from a single coded 2D projection. In addition, we demonstrate a variety of other applications for light field atoms and sparse coding, including 4D light field compression and denoising. |
| first_indexed | 2024-09-23T13:48:15Z |
| format | Article |
| id | mit-1721.1/92451 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:48:15Z |
| publishDate | 2014 |
| publisher | Association for Computing Machinery |
| record_format | dspace |
| spelling | mit-1721.1/924512022-09-28T16:19:19Z Compressive light field photography using overcomplete dictionaries and optimized projections Marwah, Kshitij Wetzstein, Gordon Bando, Yosuke Raskar, Ramesh Massachusetts Institute of Technology. Media Laboratory Program in Media Arts and Sciences (Massachusetts Institute of Technology) Marwah, Kshitij Wetzstein, Gordon Bando, Yosuke Raskar, Ramesh Light field photography has gained a significant research interest in the last two decades; today, commercial light field cameras are widely available. Nevertheless, most existing acquisition approaches either multiplex a low-resolution light field into a single 2D sensor image or require multiple photographs to be taken for acquiring a high-resolution light field. We propose a compressive light field camera architecture that allows for higher-resolution light fields to be recovered than previously possible from a single image. The proposed architecture comprises three key components: light field atoms as a sparse representation of natural light fields, an optical design that allows for capturing optimized 2D light field projections, and robust sparse reconstruction methods to recover a 4D light field from a single coded 2D projection. In addition, we demonstrate a variety of other applications for light field atoms and sparse coding, including 4D light field compression and denoising. Natural Sciences and Engineering Research Council of Canada (NSERC postdoctoral fellowship) United States. Defense Advanced Research Projects Agency (DARPA SCENICC program) Alfred P. Sloan Foundation (Sloan Research Fellowship) United States. Defense Advanced Research Projects Agency (DARPA Young Faculty Award) 2014-12-23T14:42:28Z 2014-12-23T14:42:28Z 2013-07 Article http://purl.org/eprint/type/ConferencePaper 07300301 http://hdl.handle.net/1721.1/92451 Marwah, Kshitij, Gordon Wetzstein, Yosuke Bando, and Ramesh Raskar. “Compressive Light Field Photography Using Overcomplete Dictionaries and Optimized Projections.” ACM Transactions on Graphics 32, no. 4 (July 1, 2013): 1. https://orcid.org/0000-0002-3254-3224 en_US http://dx.doi.org/10.1145/2461912.2461914 ACM Transactions on Graphics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery MIT web domain |
| spellingShingle | Marwah, Kshitij Wetzstein, Gordon Bando, Yosuke Raskar, Ramesh Compressive light field photography using overcomplete dictionaries and optimized projections |
| title | Compressive light field photography using overcomplete dictionaries and optimized projections |
| title_full | Compressive light field photography using overcomplete dictionaries and optimized projections |
| title_fullStr | Compressive light field photography using overcomplete dictionaries and optimized projections |
| title_full_unstemmed | Compressive light field photography using overcomplete dictionaries and optimized projections |
| title_short | Compressive light field photography using overcomplete dictionaries and optimized projections |
| title_sort | compressive light field photography using overcomplete dictionaries and optimized projections |
| url | http://hdl.handle.net/1721.1/92451 https://orcid.org/0000-0002-3254-3224 |
| work_keys_str_mv | AT marwahkshitij compressivelightfieldphotographyusingovercompletedictionariesandoptimizedprojections AT wetzsteingordon compressivelightfieldphotographyusingovercompletedictionariesandoptimizedprojections AT bandoyosuke compressivelightfieldphotographyusingovercompletedictionariesandoptimizedprojections AT raskarramesh compressivelightfieldphotographyusingovercompletedictionariesandoptimizedprojections |