arXiv research

A new method tracks retinal vessels more accurately than existing methods.

CycleMorph improves image registration by preserving topology with cycle consistency.

Improved image translation using asymmetric gradient guidance.

A new method for image translation without paired data.

Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.

Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.

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…

This paper addresses privacy in federated learning for medical imaging by estimating model uncertainty.

In the literature of the study of knot group epimorphisms, the existence of an epimorphism between two given knot groups is mostly (if not always) shown by giving an epimorphism which preserves meridians. A natural question arises: is there an epimorphism preserving meridians whenever a knot group is a homomorphic imag…

SASSL improves self-supervised learning by preserving image structure.

Federated CycleGAN enables privacy-preserving image translation without central data.

New diffusion models improve counterfactual image generation with semantic control.

Enhances image classification by integrating semantic hierarchy into CNN models.

Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with unpaired image-to-image translation is the ill-posed nature of the problem. In thi…

Zero-shot contrastive loss improves text-guided image style transfer without extra training.

In this paper, we propose a new variational model for image reconstruction by minimizing the $L^1$ norm of the \emph{Weingarten map} of image surface $(x,y,f(x,y))$ for a given image $f:{\mathrmΩ}\rightarrow \mathbb R$. We analytically prove that the Weingarten map minimization model can not only keep the greyscale int…

Polarimetric Synthetic Aperture Radar (PolSAR) images are establishing as an important source of information in remote sensing applications. The most complete format this type of imaging produces consists of complex-valued Hermitian matrices in every image coordinate and, as such, their visualization is challenging. Th…

DiffDenoise preserves fine structures in medical images using conditional diffusion models.

In the second, fourth and fifth authors' previous work, a duality on generic real analytic cuspidal edges in the Euclidean 3-space $\boldsymbol R^3$ preserving their singular set images and first fundamental forms, was given. Here, we call this an `isometric duality'. When the singular set image has no symmetries and d…

Image data has been greatly produced by individuals and commercial vendors in the daily life, and it has been used across various domains, like advertising, medical and traffic analysis. Recently, image data also appears to be greatly important in social utility, like emergency response. However, the privacy concern be…

A new method for image translation using disentangled style and content preservation.

InstaHide encrypts images for privacy in distributed learning.

The thesis introduces methods to use semantic hierarchy in image classification.

A new framework reduces data upload for image classification while protecting user privacy.

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable information or objects encoded in the training images, and 2) the models trained …

We describe for any Riemannian manifold a certain infinitesimal neighbourhood of the diagonal. Semi-conformal maps are analyzed as those that preserve such neighbourhoods; harmonic maps are analyzed as those that preserve mirror image formation for pairs of points in such neighbourhoods.

In this article we introduce order preserving representations of fundamental groups of surfaces into Lie groups with bi-invariant orders. By relating order preserving representations to weakly maximal representations, introduced in arXiv:1305.2620, we show that order preserving representations into Lie groups of Hermit…

The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.

Method synthesizes 4D CMR images from XCAT model using GAN and SPADE.

Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and blink behaviors. One of the challenges with regard to the social acceptance of eye tracking technology is however the preserving of sensitive …

Augmented bridge matching preserves coupling information between distributions.

ScoreAG generates unrestricted adversarial images maintaining semantic integrity.

Diffusion models generate private synthetic images with high quality.

This paper benchmarks privacy-preserving machine learning on medical images.

In this paper, we propose a new framework to remove parts of the systematic errors affecting popular restoration algorithms, with a special focus for image processing tasks. Generalizing ideas that emerged for $\ell_1$ regularization, we develop an approach re-fitting the results of standard methods towards the input d…

Boomerang generates nonidentical images similar to input on image manifolds.

Improved diffusion models for image synthesis with better training dynamics.

Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a nat…

A new method for privacy-preserving data distillation using wavelet features from ScatterNet.

Single-image super-resolution (SISR) is a canonical problem with diverse applications. Leading methods like SRGAN produce images that contain various artifacts, such as high-frequency noise, hallucinated colours and shape distortions, which adversely affect the realism of the result. In this paper, we propose an altern…

A new unsupervised method removes CT metal artifacts using beta-CycleGAN and attention.

Generative adversarial network synthesizes sketches into realistic images.

Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These complementary characteristics have stimulated active research in the inference of imag…

Framework learns image dynamics between time steps using latent variables.

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 are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard se…

Recent years have witnessed the emergence and increasing popularity of 3D medical imaging techniques with the development of 3D sensors and technology. However, achieving geometric invariance in the processing of 3D medical images is computationally expensive but nonetheless essential due to the presence of possible er…

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for th…