Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

72144215287 · Jun 202019922001200920182026
48 results for Image recovery

BCD-Net uses identical CNN structures for image recovery in undersampled imaging.

problem Challenges in obtaining accurate images from undersampled or noisy measurements.
method Incorporates image mapping CNN into BCD signal recovery method using alternating direction method of multipliers.
result Significantly more accurate image recovery compared to existing methods.

Paper proposes a new method for recovering missing samples in images.

problem Missing sample recovery in image signals.
method Iterative sparse recovery algorithm using constrained l1l_1-norm minimization with a new CSIM fidelity metric.
result Simulation results demonstrate the efficiency of the proposed method.

New method proves exact recovery for tensor decomposition under reshuffling.

problem Numerical defects limit practical applications of tensor decomposition.
method Proves exact-recovery property for latent convex tensor decomposition using reshuffling.
result Generalized LCTD achieves exact recovery under reshuffling.

Improved image reconstruction from sparse measurements using generative models.

problem Signal recovery from limited compressed measurements.
method Generative model with constrained latent variables for stable signal reconstruction.
result Improved reconstruction accuracy and preservation of realistic features.

This paper tackles tensor recovery from noisy and multi-level quantized measurements.

problem Tensors from multi-level quantized measurements.
method Nonconvex optimization problem with alternating proximal gradient descent.
result The recovery error diminishes to zero with increasing tensor dimensions.

Paper proposes a multi-task model for CECT macromolecule classification, segmentation, and recovery.

problem Challenges in recognizing and recovering macromolecular structures due to structural diversity and imaging limitations.
method A novel multi-task 3D CNN model that shares learned features across tasks.
result Multi-task model outperforms single-task methods and discovers novel structures.

Untrained neural networks can recover natural images from few measurements.

problem Recovering natural images from a small number of measurements.
method Gradient descent on un-trained convolutional neural networks.
result Untrained neural networks can approximate reconstruct signals/images from a near minimal number of random measurements.

Theoretical justification for image inpainting using diffusion models.

problem Improving sample recovery in image inpainting without retraining.
method Analysis of RePaint algorithm and proposing RePaint+^+ to correct misalignment.
result RePaint+^+ algorithm provably recovers the true sample with linear convergence.

A new method trains and samples from energy-based models using diffusion recovery likelihood.

problem Training and sampling high-dimensional datasets with energy-based models is challenging.
method Trains EBMs with a diffusion recovery likelihood method, maximizing conditional probabilities of data at different noise levels.
result Generates high-fidelity images with low FID and inception scores, and accurately estimates normalized data density.

New algorithm recovers signals from low-precision data in interferometry and imaging.

problem Signal loss in data compression for interferometry and medical imaging.
method Normalized Iterative Hard Thresholding with aggressive quantization.
result Recovery guarantees for low-precision data in compressive sensing.

Proposes a new tensor grid method for image completion.

problem Image completion from missing data.
method Low-rank tensor grid with two-stage density matrix renormalization group initialization and alternating least squares factorization.
result The proposed tensor grid method outperforms existing methods in image recovery accuracy.

Deep model learns coupled representations from side information for sparse signal recovery.

problem Recovering signals from undersampled, incomplete or noisy linear measurements.
method Deep unfolding model incorporating side information from different modalities.
result Superior performance compared to single-modal and multimodal methods.

Improved image recovery with minimal data using untrained neural networks.

problem Solving inverse problems with limited data.
method Pre-training neural networks with a small number of examples to improve performance.
result Performance increases as data increases, matching generative models with less than 1% of training data.

Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.

problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.

The paper validates a method for recovering over-parameterized matrices and images from noisy measurements.

problem Recovering a low-rank matrix from noisy measurements when the rank is unknown.
method Using gradient descent with small random initialization on a nonconvex objective function built from a rank-overspecified factored representation of the matrix variable.
result Gradient descent iterations converge to the ground-truth matrix under certain conditions and can be stopped efficiently to detect a nearly optimal estimator.

A variational Bayesian method improves image restoration in Poisson-Gaussian noise.

problem Signal recovery in the presence of non-Gaussian noise, especially Poisson-Gaussian.
method Variational Bayesian framework for estimating posterior distribution, majorization technique for non-Gaussian likelihood.
result The proposed method achieves performance comparable to manually tuned regularization parameters.

This work uses diffusion models for accurate signal recovery from semi-parametric models.

problem Recovering signals from semi-parametric single index models with discontinuous link functions.
method Proposes an efficient reconstruction method using diffusion models that requires one round of sampling and inversion.
result Demonstrates more accurate reconstructions with fewer evaluations compared to competing methods.

Empirical observations of CNN invertibility explained with a mathematical model.

problem Understanding why Convolutional Neural Networks (CNNs) are approximately invertible.
method Developed a mathematical model of sparse signal recovery consistent with random-weight CNNs, connecting to model-based compressive sensing.
result CNNs trained with random weights are consistent with the mathematical model and can be used for reasonable image reconstruction.

New algorithm uses untrained neural networks for image recovery, offering better compression.

problem Using untrained neural networks for image recovery and theoretical guarantees.
method Projected gradient descent scheme for solving linear and non-linear inverse problems.
result The method achieves better compression rates for the same image quality compared to hand-crafted priors.

A GAN-based projector speeds up image recovery in linear inverse problems.

problem Efficiently solving linear inverse problems with convergence guarantees.
method A GAN-based projector trained with projected gradient descent (PGD).
result Guaranteed O(δ)O(δ) reconstruction error in O(log(1/δ))O(log(1/δ)) steps.

The paper improves conditions for unique recovery in homomorphic sensing of subspaces.

problem Unique recovery of points in a linear subspace from their images under linear maps.
method Tighter and simpler conditions for unique recovery in single and subspace arrangement cases, extending to noise stability.
result Conditions for unique recovery in homomorphic sensing are improved and unified.

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.

PFE embeds images into sparse regions for better segmentation.

problem Image segmentation challenges with slowly varying signals and sparse region boundaries.
method Piecewise Flat Embedding (PFE) using sparse signal recovery theory, L1,p regularization, and Bregman iterations.
result PFE enhances image segmentation performance on multiple datasets.

Study on limits of recovering sparse variables from phaseless measurements.

problem Support recovery in phase retrieval model with noisy phaseless measurements.
method Information-theoretic analysis, considering discrete and Gaussian models, Gaussian measurement matrices.
result Sharp thresholds with near-matching constant factors for sparsity and signal-to-noise ratio in various scaling regimes.

This work provides a guaranteed tensor recovery method by combining low-rankness and smoothness priors.

problem Guaranteed tensor recovery with theoretical guarantees for low-rank and smoothness priors.
method Developed a new regularization term that combines low-rankness and smoothness priors, proving exact recovery guarantees.
result Rigorously proved exact recovery guarantees for tensor completion and tensor robust principal component analysis.