End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing
We present a framework for the end-to-end optimization of metasurface imaging systems that reconstruct targets using compressed sensing, a technique for solving underdetermined imaging problems when the target object exhibits sparsity (e.g., the object can be described by a small number of nonzero v...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
American Chemical Society
2024
|
| Online Access: | https://hdl.handle.net/1721.1/155313 |
| _version_ | 1811091338718871552 |
|---|---|
| author | Arya, Gaurav Li, William F. Roques-Carmes, Charles Soljačić, Marin Johnson, Steven G. Lin, Zin |
| author_facet | Arya, Gaurav Li, William F. Roques-Carmes, Charles Soljačić, Marin Johnson, Steven G. Lin, Zin |
| author_sort | Arya, Gaurav |
| collection | MIT |
| description | We present a framework for the end-to-end optimization of metasurface imaging systems that reconstruct targets using compressed sensing, a technique for solving underdetermined imaging problems when the target object exhibits sparsity (e.g., the object can be described by a small number of nonzero values, but the positions of these values are unknown). We nest an iterative, unapproximated compressed sensing reconstruction algorithm into our end-to-end optimization pipeline, resulting in an interpretable, data-efficient method for maximally leveraging metaoptics to exploit object sparsity. We apply our framework to super-resolution imaging and high-resolution depth imaging with a phase-change material. In both situations, our end-to-end framework effectively optimizes metasurface structures for compressed sensing recovery, automatically balancing a number of complicated design considerations to select an imaging measurement matrix from a complex, physically constrained manifold with millions of dimensions. The optimized metasurface imaging systems are robust to noise, significantly improving over random scattering surfaces and approaching the ideal compressed sensing performance of a Gaussian matrix, showing how a physical metasurface system can demonstrably approach the mathematical limits of compressed sensing. |
| first_indexed | 2024-09-23T15:00:54Z |
| format | Article |
| id | mit-1721.1/155313 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:00:54Z |
| publishDate | 2024 |
| publisher | American Chemical Society |
| record_format | dspace |
| spelling | mit-1721.1/1553132024-09-11T04:44:25Z End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing Arya, Gaurav Li, William F. Roques-Carmes, Charles Soljačić, Marin Johnson, Steven G. Lin, Zin We present a framework for the end-to-end optimization of metasurface imaging systems that reconstruct targets using compressed sensing, a technique for solving underdetermined imaging problems when the target object exhibits sparsity (e.g., the object can be described by a small number of nonzero values, but the positions of these values are unknown). We nest an iterative, unapproximated compressed sensing reconstruction algorithm into our end-to-end optimization pipeline, resulting in an interpretable, data-efficient method for maximally leveraging metaoptics to exploit object sparsity. We apply our framework to super-resolution imaging and high-resolution depth imaging with a phase-change material. In both situations, our end-to-end framework effectively optimizes metasurface structures for compressed sensing recovery, automatically balancing a number of complicated design considerations to select an imaging measurement matrix from a complex, physically constrained manifold with millions of dimensions. The optimized metasurface imaging systems are robust to noise, significantly improving over random scattering surfaces and approaching the ideal compressed sensing performance of a Gaussian matrix, showing how a physical metasurface system can demonstrably approach the mathematical limits of compressed sensing. Department of Defense (DoD) 2024-06-27T16:16:40Z 2024-06-27T16:16:40Z 2024-04-23 Article http://purl.org/eprint/type/JournalArticle 2330-4022 2330-4022 https://hdl.handle.net/1721.1/155313 ACS Photonics 2024, 11, 5, 2077–2087 10.1021/acsphotonics.4c00259 10.1021/acsphotonics.4c00259 ACS Photonics Creative Commons Attribution-Noncommercial-ShareAlike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf American Chemical Society Author |
| spellingShingle | Arya, Gaurav Li, William F. Roques-Carmes, Charles Soljačić, Marin Johnson, Steven G. Lin, Zin End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title | End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title_full | End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title_fullStr | End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title_full_unstemmed | End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title_short | End-to-End Optimization of Metasurfaces for Imaging with Compressed Sensing |
| title_sort | end to end optimization of metasurfaces for imaging with compressed sensing |
| url | https://hdl.handle.net/1721.1/155313 |
| work_keys_str_mv | AT aryagaurav endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing AT liwilliamf endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing AT roquescarmescharles endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing AT soljacicmarin endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing AT johnsonsteveng endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing AT linzin endtoendoptimizationofmetasurfacesforimagingwithcompressedsensing |