A fast framework for image deconvolution with incomplete observations.
problem Deconvolution with unknown boundaries is slow and artifacts-prone.
method Diagonalization of convolution operators, iterative pixel estimation and deconvolution.
result Framework allows fast deconvolution with unknown boundaries.
Deep learning improves galaxy image deconvolution in surveys.
problem Deconvolving large survey images with space-variant PSFs.
method Employed a U-Net DNN architecture for supervised galaxy image processing. Two strategies: Tikhonov deconvolution and ADMM-based iterative deconvolution.
result Deep learning approaches outperform standard convex optimization techniques in galaxy image reconstruction and shape recovery.
GANs improve galaxy image recovery beyond deconvolution limits.
problem Limited recovery of galaxy features from noisy, low-resolution images.
method Training a GAN on galaxy images to recover features from degraded data.
result GANs can recover features from degraded images better than simple deconvolution.
End-to-end image super-resolution using Attention-based DenseNet with residual deconvolution.
problem Challenging task of improving low-resolution images.
method Proposes a novel ADRD model with weighted dense blocks and spatial attention modules.
result Demonstrates promising performance on publicly available datasets.
PixelDCL addresses checkerboard problem in deconvolutional layers.
problem Checkerboard problem in deconvolutional layers.
method Fresh interpretation of deconvolution operation to establish direct relationships among adjacent pixels.
result PixelDCL can consider spatial features and yields more accurate segmentation outputs.
We present a variational Bayesian method of joint image reconstruction and point spread function (PSF) estimation when the PSF of the imaging device is only partially known. To solve this semi-blind deconvolution problem, prior distributions are specified for the PSF and the 3D image. Joint image reconstruction and PSF…
Paper improves calcium signal deconvolution using efficient state-space models.
problem Deconvolving calcium signals from imaging data.
method Dynamic compressed sensing framework with two nested EM algorithms.
result Proves recovery guarantees and derives confidence bounds for state estimates.
Network deconvolution removes redundant data to improve neural network performance.
problem Redundant data in neural networks makes training challenging.
method Network deconvolution optimally removes pixel-wise and channel-wise correlations before each layer.
result Network deconvolution improves performance across various datasets.
New method separates and deconvolves signals from single-channel mixtures.
problem Separating and deconvolving individual sources from a single-channel mixture.
method Synthesizing-decomposition (S-D) approach using GAN for sources and optimization for filters and sources.
result Achieves PSNR improvements over existing methods in various tasks.
We propose a solution to the image deconvolution problem where the convolution kernel or point spread function (PSF) is assumed to be only partially known. Small perturbations generated from the model are exploited to produce a few principal components explaining the PSF uncertainty in a high dimensional space. Unlike …
A generative Bayesian model is developed for deep (multi-layer) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up and top-down probabilistic learning. After learning the deep convolutional dictionary, testing is implemented via dec…
Deep model generates and analyzes images using hierarchical convolutional learning.
problem Representation and analysis of images.
method Hierarchical convolutional dictionary-learning framework with stochastic unpooling, Bayesian support vector machine, and deep deconvolutional inference.
result Excellent results on benchmark datasets, competitive with convolutional neural networks.
Develops a variational autoencoder for image, label, and caption modeling.
problem Deep learning of images, labels, and captions.
method Uses a Deep Generative Deconvolutional Network (DGDN) and a Convolutional Neural Network (CNN) for image and latent feature encoding.
result Able to predict labels or captions for new images using latent code distributions.
Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color information in images. Recently convolutional neural networks (CNNs), which automatica…
Paper tackles image recovery from blurry measurements using deep generative priors.
problem Jointly recovering two real-valued signals from phaseless circular convolutions.
method Alternating gradient descent algorithm with deep generative priors.
result Reconstructs quality images from blurry measurements.
New method solves sparse deconvolution problems with theoretical guarantees and practical applications.
problem Extracting localized, recurring motifs in signals with spatial or temporal structure.
method Geometric approach using sphere constraints and data-driven initialization to derive a provable algorithm.
result Practical algorithm solves real-world deconvolution problems with good performance and generalizability.
New method tackles ill-posed imaging problems with random projections.
problem Solving inverse problems with limited training data and severe ill-posedness.
method Learn an ensemble of simpler mappings to projections, then combine and deconvolve.
result More robust to noise and unseen corruptions than direct learning.
Detects object edges and assigns class labels without pixel-level annotations.
problem Semantic boundary and edge detection with image-level labels.
method Proposes a novel strategy to perform edge detection and class assignment using whole image neural nets and backpropagation.
result High pixel-wise scores indicate semantic boundary locations, suggesting edge labels are not needed during training.
A neural network predicts a body image from sensorimotor data.
problem How to acquire a body image from sensorimotor data.
method A two-branches deconvolutional neural network trained on first-person images.
result The network can automatically isolate the visible arm from the environment.
We consider an important class of signal processing problems where the signal of interest is known to be sparse, and can be recovered from data given auxiliary information about how the data was generated. For example, a sparse Green's function may be recovered from seismic experimental data using sparsity optimization…
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation. Because this problem is fundamentally ill-posed, strong priors on both the sharp image and blur kernel are required to regularize the solution space. While this naturally leads to a standard MAP estimation framework,…
New framework for disentangling graph node and edge features.
problem Learning disentangled representations for attributed graphs with node and edge features.
method Proposes a novel variational objective and architecture for node and edge deconvolutions to disentangle latent factors.
result Demonstrates effectiveness of the proposed model and its extensions on synthetic and real-world datasets.
Study Langevin Monte Carlo for sampling non-log-concave distributions.
problem Sampling from non-log-concave distributions, especially Gaussian mixtures.
method Discretizations of overdamped Langevin diffusions.
result Numerical simulations compare Langevin Monte Carlo algorithms' performance.
Intratumor heterogeneity is often manifested by vascular compartments with distinct pharmacokinetics that cannot be resolved directly by in vivo dynamic imaging. We developed tissue-specific compartment modeling (TSCM), an unsupervised computational method of deconvolving dynamic imaging series from heterogeneous tumor…
Estimation of response functions is an important task in dynamic medical imaging. This task arises for example in dynamic renal scintigraphy, where impulse response or retention functions are estimated, or in functional magnetic resonance imaging where hemodynamic response functions are required. These functions can no…
A novel Gaussian process approach for deconvolution of missing data signals.
problem Recovering a latent source from observations with missing parts and unknown filters.
method Gaussian process prior for Bayesian nonparametric deconvolution.
result The proposed Gaussian process deconvolution (GPDC) method is feasible and effective.
A new model improves analysis of neural activity from calcium imaging.
problem Statistical modeling of deconvolved calcium signals for neural activity interpretation.
method Proposed a zero-inflated gamma (ZIG) model to characterize calcium responses as a mixture of a gamma distribution and a point mass.
result The ZIG model outperforms simpler models in neural encoding and decoding problems.
Bayesian PINNs tackle uncertainty in inverse problems.
problem Uncertainty quantification in inverse problems.
method Hierarchical Bayesian formulation of PINNs with variational inference and Monte Carlo dropout.
result Quantification of uncertainties in reconstructed images.
New algorithm robustly solves blind deconvolution problems.
problem Robustly solving blind deconvolution problems in the presence of noise and perturbations.
method Mirror Descent algorithm for robust continuous optimization.
result Provable robustness and convergence guarantees for the algorithm.
RACDNN improves saliency detection by iteratively refining attention to multiple scales.
problem Saliency detection struggles with objects of varying scales.
method Recurrent attentional convolutional-deconvolution network (RACDNN) using spatial transformer and recurrent units.
result RACDNN outperforms state-of-the-art methods on saliency detection datasets.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
Natural image statistics exhibit hierarchical dependencies across multiple scales. Representing such prior knowledge in non-factorial latent tree models can boost performance of image denoising, inpainting, deconvolution or reconstruction substantially, beyond standard factorial "sparse" methodology. We derive a large …
New CNN method improves deconvolution microscopy without PSF measurement.
problem Computational expense and blind estimation in conventional deconvolution microscopy.
method Cycle consistent CNN with explicit PSF modeling layers for blind deconvolution.
result Algorithm robustness and efficacy confirmed through experimental results.
SegCaps improves object segmentation accuracy with fewer parameters.
problem Object segmentation accuracy and efficiency.
method Convolutional-deconvolutional capsule network with locally-connected routing.
result SegCaps reduces parameter space by 95.4% while improving accuracy.
Hybrid method reveals true currency correlations.
problem Identify currency status in foreign exchange networks.
method Combines DCCC and network deconvolution to filter indirect effects.
result Reflects currency status changes and is more stable.
Unified Bayesian PINN framework for solving inverse problems in infrared image processing.
problem Solving inverse problems in high-dimensional settings with complex physics.
method Bayesian Physics-Informed Neural Networks (BPINN-IP) framework, incorporating physical laws and uncertainties.
result Unified framework for physical constraints, prior knowledge, and data-driven inference with uncertainty quantification.
This paper tackles sparse blind deconvolution with short signals and demonstrates recovery of near ground truth kernels.
problem Recovering two unknown signals from their convolution, especially when one is short and sparsely supported.
method Formulated as a nonconvex optimization problem over the sphere, using a descent algorithm that escapes strict saddle points.
result Near shift truncation of the ground truth kernel can be recovered under specific conditions.
Normalizing flows improve density estimation from noisy data.
problem Estimating underlying density from noisy samples.
method Use normalizing flows for density estimation with arbitrary noise distributions, using amortized variational inference.
result Normalizing flows can outperform Gaussian mixtures for density deconvolution.
Stochastic volatility modelling of financial processes has become increasingly popular. The proposed models usually contain a stationary volatility process. We will motivate and review several nonparametric methods for estimation of the density of the volatility process. Both models based on discretely sampled continuo…
Improved text matching model using deconvolutional networks.
problem Text sequence matching challenges.
method Jointly optimizing generative and discriminative objectives with deconvolutional networks.
result Significantly outperforms sentence-encoding baselines, especially in semi-supervised settings.
New methods speed up fitting for large datasets with noisy observations.
problem Fitting large datasets with Gaussian noise and known covariance.
method Two minibatch variants of extreme deconvolution, online EM algorithm, and gradient-based optimisation.
result Methods can scale to larger models and fit larger datasets faster.
A new method corrects CTF and noise in cryo-EM images.
problem Restoring single particle cryo-EM images from noisy and distorted data.
method Covariance Wiener Filtering (CWF) method using the covariance matrix of projection images.
result CWF successfully corrects for CTF and noise, providing better image restoration.
Designs a new generative model for images using CNNs and improves generalization and performance.
problem Improving image generation and generalization in CNNs.
method Deconvolutional Generative Model (DGM) using a conjugate prior and Rendering Path Normalization (RPN).
result Improves generalization and performance in semi-supervised and supervised learning tasks.
A new method for accurately reconstructing signals without knowing the kernel or signal regularity.
problem Recovering signals from noisy measurements without prior knowledge of the convolution kernel or signal regularity.
method Parametrizing the convolution kernel and prior length-scales, jointly estimated in the inversion procedure.
result Accurate reconstructions of signals with varying regularity and unknown kernel size.
OmniFold uses deep learning to deconvolve high-dimensional simulations.
problem Removing detector distortions and accounting for noise processes in high-dimensional simulations.
method OmniFold is a deep learning-based approach for maximum likelihood deconvolution.
result OmniFold can remove detector distortions and account for noise processes and acceptance effects.
This paper develops a new method for online density estimation from noisy data.
problem Estimating probability density function from noisy streaming data.
method Quasi-Bayesian sequential deconvolution using Newton's algorithm.
result Sequential deconvolution estimate fn with large sample asymptotic guarantees. Many problems of low-level computer vision and image processing, such as denoising, deconvolution, tomographic reconstruction or super-resolution, can be addressed by maximizing the posterior distribution of a sparse linear model (SLM). We show how higher-order Bayesian decision-making problems, such as optimizing imag…
New algorithm profiles nuisance parameters for multidimensional deconvolution.
problem Statistical removal of instrumental effects in experimental measurements.
method Iterative algorithm called Profile OmniFold that profiles nuisance parameters.
result Illustrated with a Gaussian example, highlighting promising capabilities.