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.
Reduces GAN image priors' representation error using a Deep Decoder.
IAGAN method improves medical image reconstruction by incorporating adaptive GAN priors.
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is suf…
New findings suggest latent regularization is unnecessary for high-quality image generation.
The paper analyzes relationships between various image models for restoration.
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data. Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstructi…
Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned generative priors they do not require any training over large datasets. However…
Patch priors have become an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-Likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned on clean image patches as a way to regularize degraded patches. In th…
New method learns fusion rules from few images using granular ball priors.
The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For "inference", gradient descent is performed to adjust network parameters to make the output match observations. This approach yields good performance on a rang…
One of the main motivations for training high quality image generative models is their potential use as tools for image manipulation. Recently, generative adversarial networks (GANs) have been able to generate images of remarkable quality. Unfortunately, adversarially-trained unconditional generator networks have not b…
High resolution magnetic resonance (MR) images are desired for accurate diagnostics. In practice, image resolution is restricted by factors like hardware, cost and processing constraints. Recently, deep learning methods have been shown to produce compelling state of the art results for image super-resolution. Paying pa…
Compressive sensing is an impressive approach for fast MRI. It aims at reconstructing MR image using only a few under-sampled data in k-space, enhancing the efficiency of the data acquisition. In this study, we propose to learn priors based on undecimated wavelet transform and an iterative image reconstruction algorith…
Improved image reconstruction using VAEs with Student's t-prior.
Unified framework for data-driven priors in Bayesian inverse problems
Study MAP estimation for PnP priors with SGD, proving convergence and demonstrating practical applications.
Method recovers complex-valued signals from speckle-noised measurements.
Develops a robust method for image reconstruction from limited data.
BP-DIP combines DIP and backprojection for image restoration.
RG-Flow combines RG and sparse priors for hierarchical image disentanglement.
New method estimates image appearance models for segmentation.
Bayesian approach uses deep learning for seismic imaging and uncertainty quantification.
A new method uses DMs as priors for imaging problems, offering more accurate reconstructions.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
Improved computed tomography reconstruction with deep learning and deep image prior.
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…
NF-ULA combines Langevin Monte Carlo with normalizing flows for imaging inverse problems.
Improved VAEs by training a contrastive prior to match posterior.
Paper tackles image recovery from blurry measurements using deep generative priors.
Bayesian priors for neural networks are improved by incorporating weight correlations and tail behavior.
Most deep latent factor models choose simple priors for simplicity, tractability or not knowing what prior to use. Recent studies show that the choice of the prior may have a profound effect on the expressiveness of the model,especially when its generative network has limited capacity. In this paper, we propose to lear…
This paper improves image super-resolution by integrating cross-scale non-local attention.
GANs as priors improve uncertainty quantification in complex fields.
Unified framework for image restoration using equivariant denoisers.
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 …
Bayesian imaging uses neural networks to learn prior knowledge from data.
The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors drawn from a prior distribution into realistic looking photos. These latent vectors have been shown to encode information about the content of their corresponding images. Projecting input images onto the latent space of a GAN…
New method uses deep learning to solve linear inverse problems.
Purpose: Conventional automated segmentation of the head anatomy in MRI distinguishes different brain and non-brain tissues based on image intensities and prior tissue probability maps (TPM). This works well for normal head anatomies, but fails in the presence of unexpected lesions. Deep convolutional neural networks l…
This paper improves image retrieval accuracy through novel relevance feedback methods.
DP-RandP improves privacy-utility tradeoff in DP-SGD by learning priors from random processes.
Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlyin…
Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis. By representing a test pixel as a linear combination of a small subset of labeled pixels, a sparse representation classifier (SRC) gives rather plausible results …
Unified sampling approach for Bayesian imaging problems.
This paper presents a Bayesian image segmentation model based on Potts prior and loopy belief propagation. The proposed Bayesian model involves several terms, including the pairwise interactions of Potts models, and the average vectors and covariant matrices of Gauss distributions in color image modeling. These terms a…
A geometric account explains why 'The Dress' is ambiguous, predicting observable signatures in image processing.
Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior inform…
DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.