Related papers: TFDWT: Fast Discrete Wavelet Transform TensorFlow …

Low-light image enhancement techniques have significantly progressed, but unstable image quality recovery and unsatisfactory visual perception are still significant challenges. To solve these problems, we propose a novel and robust…

Facing the diversity and growth of the musical field nowadays, the search for precise songs becomes more and more complex. The identity of the singer facilitates this search. In this project, we focus on the problem of identifying the…

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…

Full Waveform Inversion (FWI) is an important geophysical technique considered in subsurface property prediction. It solves the inverse problem of predicting high-resolution Earth interior models from seismic data. Traditional FWI methods…

The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as the high costs associated with frequent observations. These challenges hinder applications…

In this paper we outline several points of view on the interplay between discrete and continuous wavelet transforms; stressing both pure and applied aspects of both. We outline some new links between the two transform technologies based on…

We developed a lightweight and computationally efficient tool for next-day wildfire spread prediction using multimodal satellite data as input. The deep learning model, which we call Transform Domain Fusion UNet (TD-FusionUNet),…

Multivariate time-series (MTS) forecasting is fundamental to applications ranging from urban mobility and resource management to climate modeling. While recent generative models based on denoising diffusion have advanced state-of-the-art…

A wave view of the universe is proposed in which each natural phenomenon is equipped with its own unique natural viewing lens. A self-sameness modeling principle and its systematic application in Fourier-Laplace transform space is proposed…

Full Waveform Inversion (FWI) is a powerful technique for estimating high-resolution subsurface velocity models by minimizing the discrepancy between modeled and observed seismic data. However, the oscillatory nature of seismic waveforms…

Differentiable Wavetable Synthesis (DWTS) is a technique for neural audio synthesis which learns a dictionary of one-period waveforms i.e. wavetables, through end-to-end training. We achieve high-fidelity audio synthesis with as little as…

Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and…

We present DeepTract, a deep-learning framework for estimating white matter fibers orientation and streamline tractography. We adopt a data-driven approach for fiber reconstruction from diffusion weighted images (DWI), which does not assume…

While deep learning-based models like transformers, have revolutionized time-series and vision tasks, they remain highly susceptible to noise and often overfit on noisy patterns rather than robust features. This issue is exacerbated in…

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this…

Generative diffusion models have received increasing attention in medical imaging, particularly in limited-angle computed tomography (LACT). Standard diffusion models achieve high-quality image reconstruction but require a large number of…

Imaginary-time time-dependent Density functional theory (it-TDDFT) has been proposed as an alternative method for obtaining the ground state within density functional theory (DFT) which avoids some of the difficulties with convergence…

GPU-based fast Fourier transform (FFT) is extremely important for scientific computing and signal processing. However, we find the inefficiency of existing FFT libraries and the absence of fault tolerance against soft error. To address…

The feature learning methods based on convolutional neural network (CNN) have successfully produced tremendous achievements in image classification tasks. However, the inherent noise and some other factors may weaken the effectiveness of…

Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimensional data with two key aspects. First, our TWD is specifically…