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.
Paper introduces LLISE for image structure learning using SSIM.
CatSIM measures image similarity robustly to small changes.
Proposes a new PCA method using SSIM for image subspace learning.
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures. The main reason is that most of the current generative models fail to explore the structures in the images including spatial layout and semantic relations betwe…
Satellite images improve real-estate price predictions.
Image compression techniques reveal network structure for shipping box optimization.
A new method transcribes complex structured images like musical scores.
In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) into iterative image recovery has great potential to resolve this issue. This pape…
New method reconstructs 3D protein structures from cryo-EM images.
P3I learns holistic scene representations from a single image.
We describe a model for capturing the statistical structure of local amplitude and local spatial phase in natural images. The model is based on a recently developed, factorized third-order Boltzmann machine that was shown to be effective at capturing higher-order structure in images by modeling dependencies among squar…
Spectral images captured by satellites and radio-telescopes are analyzed to obtain information about geological compositions distributions, distant asters as well as undersea terrain. Spectral images usually contain tens to hundreds of continuous narrow spectral bands and are widely used in various fields. But the vast…
M2M tackles zero-shot structured noise suppression in images.
Positron Emission Tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as Magnetic Resonance (MR) images…
New method predicts drug interactions from drug images.
New technique halves scan time for multi-echo MR images.
PG-IM uses neural-symbolic programs to manipulate images.
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resol…
Structural RBM reduces parameters for image denoising and classification.
A GMM-based method generates new 3D structures from medical images.
Paper proposes ASR framework to improve image generation by incorporating human knowledge.
IAGAN method improves medical image reconstruction by incorporating adaptive GAN priors.
DiffDenoise preserves fine structures in medical images using conditional diffusion models.
Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures perfusion of the…
A network removes irrelevant structures from chest radiographs for better analysis.
Convolutional networks can denoise images without training data.
In this paper we classify all Moishezon twistor spaces on 4CP^2. The classification is given in terms of the structure of the anticanonical system of the twistor spaces. We show that the anticanonical map satisfies one of the following three properties: (a) birational over the image, (b) two to one over the image, or (…
SNS-GAN integrates class labels into generative models for images and time series.
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…
We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the pow…
ECN framework improves training on noisy structured labels.
Deep-learning method estimates bone 3D structure from X-ray images.
Method screens similar capsule endoscopic images, reducing doctor workload and improving accuracy.
Proves a tree of shapes for n-D images in optimal time.
Low-dimensional structure in images helps deep learning models generalize better.
This paper tackles non-convex phase retrieval with structured assumptions.
ME-Net defends neural nets against adversarial attacks by reconstructing images.
Hexnet framework enhances image processing with hexagonal structures.
Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictionary, is learned to adapt to specific data. This approach has proven to be very effective in many image processing tasks. Traditionally, the di…
Efficiently transfers style to content without distorting the content structure.
Sparse representations using overcomplete dictionaries have proved to be a powerful tool in many signal processing applications such as denoising, super-resolution, inpainting, compression or classification. The sparsity of the representation very much depends on how well the dictionary is adapted to the data at hand. …
This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicting diagonal covariance matrices. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits …
We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for a probabilistic interpretation of cell and nuclear morphology and structure loca…
Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution. Although template matching is often used to locate macromolecules in a CECT imag…
Generative models improve MRI reconstruction by learning image structure.
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…
Learning the distribution of natural images is one of the hardest and most important problems in machine learning. The problem remains open, because the enormous complexity of the structures in natural images spans all length scales. We break down the complexity of the problem and show that the hierarchy of structures …
BPI models 2D patterns on multiple planes and 3D scene from a single image.