Efficient algorithms for convolutional inverse problems in multidimensional imaging

2020
Doğan, Didem
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 algorithms that exploit sparse models in analysis and synthesis forms. These priors involve sparsifying transforms or data-adaptive dictionaries that are patch-based and convolutional. The numerical performance of the developed algorithms is evaluated for a three-dimensional image reconstruction problem in spectral imaging. The results demonstrate the superiority of the convolutional dictionary prior over others. The developed algorithms are also extended to the compressive setting with compressed convolutional measurements.

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...
Image fusion for improving spatial resolution of multispectral satellite images
Ünlüsoy, Deniz; Süzen, Mehmet Lütfi; Department of Geological Engineering (2013)
In this study, four different image fusion techniques have been applied to high spectral and low spatial resolution satellite images with high spatial and low spectral resolution images to obtain fused images with increased spatial resolution, while preserving spectral information as much as possible. These techniques are intensity-hue-saturation (IHS) transform, principle component analysis (PCA), Brovey transform (BT), and Wavelet transform (WT) image fusion. Images used in the study belong to Çankırı reg...
Alignment of uncalibrated images for multi-view classification
Arık, Sercan Ömer; Vural, Elif; Frossard, Pascal (2011-12-29)
Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pairwise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of im...
Iterative Photometric Stereo with Shadow and Specular Region Detection for 3D Reconstruction
BUYUKATALAY, Soner; BİRGÜL, ÖZLEM; Halıcı, Uğur (2009-04-11)
Photometric stereo is a 3D reconstruction algorithm that uses the images of an object with different light conditions and its performance is affected by the shades and specular regions in the images. Especially, the use of Lambert reflectance model results in errors in the reconstructed surface normals. In this study an iterative approach was used to generate masks corresponding to these problematic regions and the surface normals were reconstructed using a Lambert based algorithm that excludes these region...
Compressive spectral imaging using diffractive lenses and multi-spectral sensors with learned reconstruction and joint optimization
Gündoğan, Utku; Öktem, Sevinç Figen; Department of Electrical and Electronics Engineering (2022-2)
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 ...
Citation Formats
D. Doğan, “Efficient algorithms for convolutional inverse problems in multidimensional imaging,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Electrical and Electronics Engineering., Middle East Technical University, 2020.