Compressive spectral imaging using diffractive lenses and multi-spectral sensors with learned reconstruction and joint optimization

2022-2
Gündoğan, Utku
Compressive spectral imaging aims to reconstruct the entire three-dimensional spectral cube from a few measurements, ideally with a snapshot capability. Recently various spectral imaging modalities have been developed by exploiting diffractive lenses. Another line of development in this area is enabled by spectral filter arrays which resulted in multi-spectral sensors. In this thesis, we first review an existing compressive spectral imaging modality with diffractive lenses and analyze its performance using some quantitative metrics. We then study the joint reconstruction and system optimization for this imaging modality using a model-based learned approach with an unrolled deep neural network (DNN). Secondly, we improve on this modality by developing a new spectral imaging system that also exploits a multi-spectral sensor. To reconstruct the spectral cube from its compressive measurements, we design a learned reconstruction method using a similar unrolled network. A fast sparse reconstruction algorithm is also developed and compared with this learned reconstruction method. The performance of the developed imaging technique is illustrated for the visible regime using different design configurations, number of measurements, and signal-to-noise ratios. The results demonstrate that significant performance improvement can be achieved over the existing compressive spectral imaging modality with diffractive lenses, while also enabling snapshot capability with a simpler design.

Suggestions

DEEP LEARNING-BASED UNROLLED RECONSTRUCTION METHODS FOR COMPUTATIONAL IMAGING
Bezek, Can Deniz; Öktem, Sevinç Figen; Department of Electrical and Electronics Engineering (2021-9-08)
Computational imaging is the process of forming images from indirect measurements using computation. In this thesis, we develop deep learning-based unrolled reconstruction methods for various computational imaging modalities. Firstly, we develop two deep learning-based reconstruction methods for diffractive multi-spectral imaging. The first approach is based on plug-and-play regularization with deep denoisers whereas the second one is an end-to-end learned reconstruction based on unrolling. Secondly, we con...
Anlık Spektral Görüntüleme için Tasarım Eniyileme
Ayazgök, Suleyman; Öktem, Sevinç Figen (2019-08-22)
Snapshot spectral imaging enables to reconstructspectral images from a multiplexed single-shot measurement.Since an inversion is required to form the spectral images com-putationally, quantitative characterization of their performanceis essential to optimize the design. In this paper, we analyze theoptimal design of a snapshot spectral imaging technique. Thissnapshot multi-spectral imaging technique uses a diffractive lenscalled generalized photon sieve, and vari...
Compressive spectral imaging with diffractive lenses
Kar, Oguzhan Fatih; Öktem, Sevinç Figen (The Optical Society, 2019-09-15)
Compressive spectral imaging enables the reconstruction of an entire 3D spectral cube from a few multiplexed images. Here we develop a novel compressive spectral imaging technique using diffractive lenses. Our technique uses a coded aperture to spatially modulate the optical field from the scene and a diffractive lens such as a photon sieve for both dispersion and focusing. Measurement diversity is achieved by changing the focusing behavior of the diffractive lens. The 3D spectral cube is then reconstructed...
Compressive Photon-Sieve Spectral Imaging
Kar, Oguzhan Fatih; Kamaci, Ulas; Akyon, Fatih; Öktem, Sevinç Figen (2018-06-25)
We develop a new compressive spectral imaging modality that utilizes a coded aperture and a photon-sieve for dispersion. The 3D spectral data cube is successfully reconstructed with as little as two shots using sparse recovery
Efficient algorithms for convolutional inverse problems in multidimensional imaging
Doğan, Didem; Öktem, Figen S.; Department of Electrical and Electronics Engineering (2020)
Computational imaging is the process of indirectly forming images from measurements using image reconstruction algorithms that solve inverse problems. In many inverse problems in multidimensional imaging such as spectral and depth imaging, the measurements are in the form of superimposed convolutions related to the unknown image. In this thesis, we first provide a general formulation for these problems named as convolutional inverse problems, and then develop fast and efficient image reconstruction algorith...
Citation Formats
U. Gündoğan, “Compressive spectral imaging using diffractive lenses and multi-spectral sensors with learned reconstruction and joint optimization,” M.S. - Master of Science, Middle East Technical University, 2022.