Publications

Block Coordinate Regularization by Denoising

Published in arXiv (cs.CV), 2019

We consider the problem of estimating a vector from its noisy measurements using a prior specified only through a denoising function. Recent work on plug-and-play priors (PnP) and regularization-by-denoising (RED) has shown the state-of-the-art performance of estimators under such priors in a range of imaging tasks. In this work, we develop a new block coordinate RED algorithm that decomposes a large-scale estimation problem into a sequence of updates over a small subset of the unknown variables. We theoretically analyze the convergence of the algorithm and discuss its relationship to the traditional proximal optimization. Our analysis complements and extends recent theoretical results for RED-based estimation methods. We numerically validate our method using several denoiser priors, including those based on convolutional neural network (CNN) denoisers.

Recommended citation: Y. Sun, J. Liu, and U. S. Kamilov, "Block Coordinate Regularization by Denoising" arXiv:1905.05113. https://128.84.21.199/abs/1905.05113

Image Restoration using Total Variation Regularized Deep Image Prior

Published in arXiv (cs.CV), 2018

In the past decade, sparsity-driven regularization has led to significant improvements in image reconstruction. Traditional regularizers, such as total variation (TV), rely on analytical models of sparsity. However, increasingly the field is moving towards trainable models, inspired from deep learning. Deep image prior (DIP) is a recent regularization framework that uses a convolutional neural network (CNN) architecture without data-driven training. This paper extends the DIP framework by combining it with the traditional TV regularization. We show that the inclusion of TV leads to considerable performance gains when tested on several traditional restoration tasks such as image denoising and deblurring.

Recommended citation: J. Liu, Y. Sun, X. Xu, and U. S. Kamilov, "Image Restoration using Total Variation Regularized Deep Image Prior." Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. (ICASSP 2019) (Brighton, UK, May 12-17), in press https://arxiv.org/abs/1810.12864

Regularized Fourier Ptychography Using An Online Plug-and-play Algorithm

Published in arXiv (cs.CV), 2018

The plug-and-play priors (PnP) framework has been recently shown to achieve state-of-the-art results in regularized image reconstruc- tion by leveraging a sophisticated denoiser within an iterative algo- rithm. In this paper, we propose a new online PnP algorithm for Fourier ptychographic microscopy (FPM) based on the fast iterative shrinkage/threshold algorithm (FISTA). Specifically, the proposed algorithm uses only a subset of measurements, which makes it scal- able to a large set of measurements. We validate the algorithm by showing that it can lead to significant performance gains on both simulated and experimental data.

Recommended citation: Y. Sun, Shiqi Xu, Yunzhe Li, Lei Tian, B. Wohlberg, and U. S. Kamilov, "Regularized Fourier Ptychography Using An Online Plug-and-play Algorithm." Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. (ICASSP 2019) (Brighton, UK, May 12-17), in press. https://arxiv.org/abs/1811.00120

An Online Plug-and-Play Algorithm for Regularized Image Reconstruction

Published in arXiv (cs.CV), 2018

Plug-and-play priors (PnP) is a powerful framework for regularizing imaging inverse problems by using advanced denoisers within an iterative algorithm. Recent experimental evidence suggests that PnP algorithms achieve state-of-the-art performance in a range of imaging applications. In this paper, we introduce a new online PnP algorithm based on the iterative shrinkage/thresholding algorithm (ISTA). The proposed algorithm uses only a subset of measurements at every iteration, which makes it scalable to very large datasets. We present a new theoretical convergence analysis, for both batch and online variants of PnP-ISTA, for denoisers that do not necessarily correspond to proximal operators. We also present simulations illustrating the applicability of the algorithm to image reconstruction in diffraction tomography. The results in this paper have the potential to expand the applicability of the PnP framework to very large and redundant datasets.

Recommended citation: Y. Sun, B. Wohlberg, and U. S. Kamilov, "An Online Plug-and-Play Algorithm for Regularized Image Reconstruction." IEEE Trans. Comput. Imag. https://arxiv.org/abs/1809.04693

Stability of Scattering Decoder For Nonlinear Diffractive Imaging

Published in Proc. iTWIST, 2018

The problem of image reconstruction under multiple light scattering is usually formulated as a regularized nonconvex optimization. A deep learning architecture, Scattering Decoder (ScaDec), was recently proposed "Efficent and accurate inversion of multiple scattering with deep learning" to solve this problem in a purely data-driven fashion. The proposed method was shown to substantially outperform optimization-based baselines and achieve state-of-the-art results. In this paper, we thoroughly test the robustness of ScaDec to different permittivity contrasts, number of transmissions, and input signal-to-noise ratios. The results on high-fidelity simulated datasets show that the performance of the ScaDec is stable in different settings.

Recommended citation: Y. Sun and U. S. Kamilov. "Stability of Scattering Decoder For Nonlinear Diffractive Imaging."(Oral) iTWIST 2018. https://arxiv.org/abs/1806.08015

Efficient and accurate inversion of multiple scattering with deep learning

Published in Optics Express, 2018

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.

Recommended citation: Y. Sun, Z. Xia, and U. S. Kamilov, “Efficient and accurate inversion of multiple scattering with deep learning,” Opt. Express, vol. 26, no. 11, pp. 14678-14688, May 2018. https://github.com/sunyumark/ScaDec-deep-learning-diffractive-tomography