Denoiser-based projections for 2-D super-resolution multi-reference alignment

We study the 2-D super-resolution multi-reference alignment (SR-MRA) problem: estimating an image from its down-sampled, circularly-translated, and noisy copies. The SR-MRA problem serves as a mathematical abstraction of the structure determination problem for biological molecules. Since the SR-MRA problem is ill-posed without prior knowledge, accurate image estimation relies on designing priors that well-describe the statistics of the images of interest. In this work, we build on recent advances in image processing, and harness the power of denoisers as priors of images. In particular, we suggest to use denoisers as projections, and design two computational frameworks to estimate the image: projected expectation-maximization and projected method of moments. We provide an efficient GPU implementation, and demonstrate the effectiveness of these algorithms by extensive numerical experiments on a wide range of parameters and images.

[1]  A. Singer,et al.  A stochastic approximate expectation-maximization for structure determination directly from cryo-EM micrographs , 2023, 2303.02157.

[2]  Tamir Bendory,et al.  Dihedral Multi-Reference Alignment , 2021, IEEE Transactions on Information Theory.

[3]  Tamir Bendory,et al.  Compactification of the Rigid Motions Group in Image Processing , 2021, SIAM J. Imaging Sci..

[4]  Tamir Bendory,et al.  An Accelerated Expectation-Maximization Algorithm for Multi-Reference Alignment , 2021, IEEE Transactions on Signal Processing.

[5]  Tamir Bendory,et al.  An accelerated expectation-maximization for multi-reference alignment , 2021, ArXiv.

[6]  Tamir Bendory,et al.  The Generalized Method of Moments for Multi-Reference Alignment , 2021, IEEE Transactions on Signal Processing.

[7]  Yonina C. Eldar,et al.  Image Restoration by Deep Projected GSURE , 2021, 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

[8]  Einav Yogev-Ofer,et al.  An Interpretation Of Regularization By Denoising And Its Application With The Back-Projected Fidelity Term , 2021, 2021 IEEE International Conference on Image Processing (ICIP).

[9]  Luc Van Gool,et al.  Plug-and-Play Image Restoration With Deep Denoiser Prior , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Amit Singer,et al.  Super-resolution multi-reference alignment , 2020, Information and inference : a journal of the IMA.

[11]  Alexandros G. Dimakis,et al.  Deep Learning Techniques for Inverse Problems in Imaging , 2020, IEEE Journal on Selected Areas in Information Theory.

[12]  Carola-Bibiane Schönlieb,et al.  Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination , 2020, bioRxiv.

[13]  Angelica I. Avilés-Rivero,et al.  Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems , 2020, ICML.

[14]  Amit Singer,et al.  Single-Particle Cryo-Electron Microscopy: Mathematical Theory, Computational Challenges, and Opportunities , 2019, IEEE Signal Processing Magazine.

[15]  Amit Singer,et al.  Method of moments for 3D single particle ab initio modeling with non-uniform distribution of viewing angles , 2019, Inverse Problems.

[16]  Xiaohan Chen,et al.  Plug-and-Play Methods Provably Converge with Properly Trained Denoisers , 2019, ICML.

[17]  Tom Tirer,et al.  Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning , 2018, IEEE Signal Processing Letters.

[18]  Amit Singer,et al.  Toward single particle reconstruction without particle picking: Breaking the detection limit , 2018, bioRxiv.

[19]  Brendt Wohlberg,et al.  An Online Plug-and-Play Algorithm for Regularized Image Reconstruction , 2018, IEEE Transactions on Computational Imaging.

[20]  R. Gribonval,et al.  A Characterization of Proximity Operators , 2018, Journal of Mathematical Imaging and Vision.

[21]  Philip Schniter,et al.  Regularization by Denoising: Clarifications and New Interpretations , 2018, IEEE Transactions on Computational Imaging.

[22]  Afonso S. Bandeira,et al.  Estimation under group actions: recovering orbits from invariants , 2017, Applied and Computational Harmonic Analysis.

[23]  Amit Singer,et al.  3D ab initio modeling in cryo-EM by autocorrelation analysis , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[24]  R. Giryes,et al.  Image Restoration by Iterative Denoising and Backward Projections , 2017, IEEE Transactions on Image Processing.

[25]  Hassan Mansour,et al.  A Plug-and-Play Priors Approach for Solving Nonlinear Imaging Inverse Problems , 2017, IEEE Signal Processing Letters.

[26]  Amit Singer,et al.  Multireference Alignment Is Easier With an Aperiodic Translation Distribution , 2017, IEEE Transactions on Information Theory.

[27]  Roy R. Lederman,et al.  Heterogeneous multireference alignment: A single pass approach , 2017, 2018 52nd Annual Conference on Information Sciences and Systems (CISS).

[28]  Amir Beck,et al.  First-Order Methods in Optimization , 2017 .

[29]  Stanley H. Chan,et al.  Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibrium , 2017, SIAM J. Imaging Sci..

[30]  Zhizhen Zhao,et al.  Bispectrum Inversion With Application to Multireference Alignment , 2017, IEEE Transactions on Signal Processing.

[31]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Michael Möller,et al.  Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[33]  David J. Fleet,et al.  cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination , 2017, Nature Methods.

[34]  Michael Elad,et al.  The Little Engine That Could: Regularization by Denoising (RED) , 2016, SIAM J. Imaging Sci..

[35]  John J. Leonard,et al.  SE-Sync: A certifiably correct algorithm for synchronization over the special Euclidean group , 2016, Int. J. Robotics Res..

[36]  Stanley H. Chan,et al.  Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications , 2016, IEEE Transactions on Computational Imaging.

[37]  Michael Elad,et al.  Poisson Inverse Problems by the Plug-and-Play scheme , 2015, J. Vis. Commun. Image Represent..

[38]  Michael Elad,et al.  Postprocessing of Compressed Images via Sequential Denoising , 2015, IEEE Transactions on Image Processing.

[39]  Yutong Chen,et al.  NON-UNIQUE GAMES OVER COMPACT GROUPS AND ORIENTATION ESTIMATION IN CRYO-EM , 2015, Inverse problems.

[40]  Brendt Wohlberg,et al.  Plug-and-Play priors for model based reconstruction , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[41]  Sjors H.W. Scheres,et al.  RELION: Implementation of a Bayesian approach to cryo-EM structure determination , 2012, Journal of structural biology.

[42]  Gregory S. Chirikjian,et al.  A stochastic kinematic model of class averaging in single-particle electron microscopy , 2011, Int. J. Robotics Res..

[43]  Peyman Milanfar,et al.  Optimal Registration Of Aliased Images Using Variable Projection With Applications To Super-Resolution , 2008, Comput. J..

[44]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[45]  A. Antoniadis,et al.  Poisson inverse problems , 2006, math/0601099.

[46]  Manuel Rosa-Zurera,et al.  Using Multilayer Perceptrons to Align High Range Resolution Radar Signals , 2005, ICANN.

[47]  Roberto Marabini,et al.  Maximum-likelihood multi-reference refinement for electron microscopy images. , 2005, Journal of molecular biology.

[48]  I. Yamada,et al.  Hybrid Steepest Descent Method for Variational Inequality Problem over the Fixed Point Set of Certain Quasi-nonexpansive Mappings , 2005 .

[49]  F. Groen,et al.  Fast Translation Invariant Classification of (HRR) Range Profiles in a Zero Phase Representation , 2003 .

[50]  R. Henderson.  The potential and limitations of neutrons, electrons and X-rays for atomic resolution microscopy of unstained biological molecules , 1995, Quarterly Reviews of Biophysics.

[51]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[52]  Marc Teboulle,et al.  Gradient-based algorithms with applications to signal-recovery problems , 2010, Convex Optimization in Signal Processing and Communications.

[53]  J. Moreau.  Proximité et dualité dans un espace hilbertien , 1965 .