Related papers: Artifact reduction in pseudo-acoustic modeling by …
Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…
Coarse-grained models that preserve hydrodynamics provide a natural approach to study collective properties of soft-matter systems. Here, we demonstrate that commonly used integration schemes in dissipative particle dynamics give rise to…
With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…
Numerical modeling of elastic wave propagation in the subsurface requires applicability to heterogeneous, anisotropic and discontinuous media, as well as support of free surface boundary conditions. Here we study the cell-centered finite…
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation…
The rapid evolution of deepfake technologies demands robust and reliable face forgery detection algorithms. While determining whether an image has been manipulated remains essential, the ability to precisely localize forgery clues is also…
We show how the notion of message passing can be used to streamline the algebra and computer coding for fast approximate inference in large Bayesian semiparametric regression models. In particular, this approach is amenable to handling…
Underwater automatic target recognition (UATR) has been a challenging research topic in ocean engineering. Although deep learning brings opportunities for target recognition on land and in the air, underwater target recognition techniques…
Application of transformation theory to underwater acoustics has been a challenging task because highly anisotropic density is unachievable in water. A possible strategy is to exploit anisotropic modulus rather than density, while has not…
A lesser-known but powerful application of parabolic equation methods is to the target scattering problem. In this paper, we use noncanonically shaped objects to establish the limits of applicability of the traditional approach, and…
Optical wavefront-shaping has emerged as a powerful tool to manipulate light in strongly scattering media. It enables diffraction-limited focusing and imaging at depths where conventional microscopy techniques fail. However, while most…
For several years, numerous attempts have been made to reduce noise and artifacts in MRI. Although there have been many successful methods to address these problems, practical implementation for clinical images is still challenging because…
The formation of shear shock waves in the brain has been proposed as one of the plausible explanations for deep intracranial injuries. In fact, such singular solutions emerge naturally in soft viscoelastic tissues under dynamic loading…
Neural style transfer (NST) has evolved significantly in recent years. Yet, despite its rapid progress and advancement, existing NST methods either struggle to transfer aesthetic information from a style effectively or suffer from high…
Image denoising or artefact removal using deep learning is possible in the availability of supervised training dataset acquired in real experiments or synthesized using known noise models. Neither of the conditions can be fulfilled for…
In this paper, we discuss a virtual element approximation for the modified transmission eigenvalue problem in inverse scattering for natural materials. In this case, due to the positive artificial diffusivity parameter in the considered…
The widespread use of AI-generated content from diffusion models has raised significant concerns regarding misinformation and copyright infringement. Watermarking is a crucial technique for identifying these AI-generated images and…
Ptychographic phase retrieval enables high-resolution imaging of complex samples but often suffers from artifacts such as grid pathology and multislice crosstalk, which degrade reconstructed images. We propose a plug-and-play (PnP)…
Score-based diffusion models have significantly advanced generative deep learning for image processing. Measurement conditioned models have also been applied to inverse problems such as CT reconstruction. However, the conventional approach,…
We consider the numerical approximation of acoustic wave propagation in the time domain by a mixed finite element method based on the BDM1-P0 spaces. A mass-lumping strategy for the BDM1 element, originally proposed by Wheeler and Yotov in…