中文
相关论文

相关论文: PAC-FNO: Parallel-Structured All-Component Fourier…

200 篇论文

Partial differential equations (PDEs) govern a wide variety of dynamical processes in science and engineering, yet obtaining their numerical solutions often requires high-resolution discretizations and repeated evaluations of complex…

机器学习 · 计算机科学 2026-01-26 Valentin Duruisseaux , Jean Kossaifi , Anima Anandkumar

A neural network is essentially a high-dimensional complex mapping model by adjusting network weights for feature fitting. However, the spectral bias in network training leads to unbearable training epochs for fitting the high-frequency…

信号处理 · 电气工程与系统科学 2021-06-22 Zhi Zeng , Pengpeng Shi , Fulei Ma , Peihan Qi

Classical sequential models employed in time-series prediction rely on learning the mappings from the past to the future instances by way of a hidden state. The Hidden states characterise the historical information and encode the required…

机器学习 · 计算机科学 2023-02-14 Vignesh Gopakumar , Stanislas Pamela , Lorenzo Zanisi

Fourier Neural Operators (FNOs) have emerged as promising surrogates for partial differential equation solvers. In this work, we extensively tested FNOs on a variety of systems with non-linear and non-stationary properties, using a wide…

计算工程、金融与科学 · 计算机科学 2025-11-13 Rad Haghi , Bipin Gaikwad , Abani Patra

Neural operators can learn nonlinear mappings between function spaces and offer a new simulation paradigm for real-time prediction of complex dynamics for realistic diverse applications as well as for system identification in science and…

Data-driven surrogates can replace expensive multiphysics solvers for parametric PDEs, yet building compact, accurate neural operators for three-dimensional problems remains challenging: in Fourier Neural Operators, dense mode-wise spectral…

量子物理 · 物理学 2026-04-07 Mateusz Papierz , Asel Sagingalieva , Alix Benoit , Toni Ivas , Elia Iseli , Alexey Melnikov

Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural…

声音 · 计算机科学 2022-04-08 Ivan Shchekotov , Pavel Andreev , Oleg Ivanov , Aibek Alanov , Dmitry Vetrov

Partial scan is a common approach to accelerate Magnetic Resonance Imaging (MRI) data acquisition in both 2D and 3D settings. However, accurately reconstructing images from partial scan data (i.e., incomplete k-space matrices) remains…

图像与视频处理 · 电气工程与系统科学 2023-06-06 Xiaohan Liu , Yanwei Pang , Xuebin Sun , Yiming Liu , Yonghong Hou , Zhenchang Wang , Xuelong Li

Memory complexity and data scarcity have so far prohibited learning solution operators of partial differential equations (PDEs) at high resolutions. We address these limitations by introducing a new data efficient and highly parallelizable…

机器学习 · 计算机科学 2023-10-03 Jean Kossaifi , Nikola Kovachki , Kamyar Azizzadenesheli , Anima Anandkumar

Low-light image enhancement is a classical computer vision problem aiming to recover normal-exposure images from low-light images. However, convolutional neural networks commonly used in this field are good at sampling low-frequency local…

计算机视觉与模式识别 · 计算机科学 2022-09-19 Yunliang Zhuang , Zhuoran Zheng , Chen Lyu

Flexible intelligent metasurfaces (FIMs) offer a new solution for wireless communications by introducing morphological degrees of freedom, dynamically morphing their three-dimensional shape to ensure multipath signals interfere…

信息论 · 计算机科学 2026-04-08 Jian Xiao , Ji Wang , Qimei Cui , Yucang Yang , Xingwang Li , Dusit Niyato , Chau Yuen

All-in-One Image Restoration (AIO-IR) aims to develop a unified model that can handle multiple degradations under complex conditions. However, existing methods often rely on task-specific designs or latent routing strategies, making it hard…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Jingren Liu , Shuning Xu , Qirui Yang , Yun Wang , Xiangyu Chen , Zhong Ji

A major challenge in computed tomography is reconstructing objects from incomplete data. An increasingly popular solution for these problems is to incorporate deep learning models into reconstruction algorithms. This study introduces a…

数值分析 · 数学 2024-02-20 Knut Salomonsson , Eric Oldgren , Emanuel Ström , Ozan Öktem

Fourier ptychography has attracted a wide range of focus for its ability of large space-bandwidth-produce, and quantative phase measurement. It is a typical computational imaging technique which refers to optimizing both the imaging…

图像与视频处理 · 电气工程与系统科学 2022-03-08 Guocheng Zhou , Shaohui Zhang , Yao Hu , Lei Cao , Yong Huang , Qun Hao

Diffusion generative models have achieved remarkable success in generating images with a fixed resolution. However, existing models have limited ability to generalize to different resolutions when training data at those resolutions are not…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Alex Havrilla , Kevin Rojas , Wenjing Liao , Molei Tao

Fourier ptychography is a recently explored imaging method for overcoming the diffraction limit of conventional cameras with applications in microscopy and yielding high-resolution images. In order to splice together low-resolution images…

图像与视频处理 · 电气工程与系统科学 2020-03-18 Yican Chen , Zhi Luo , Xia Wu , Huidong Yang , Bo Huang

Object recognition systems are usually trained and evaluated on high resolution images. However, in real world applications, it is common that the images have low resolutions or have small sizes. In this study, we first track the…

计算机视觉与模式识别 · 计算机科学 2023-03-15 Amir Ghasemi , Nasrin Bayat , Fatemeh Mottaghian , Akram Bayat

Predicting plasma evolution within a Tokamak is crucial to building a sustainable fusion reactor. Whether in the simulation space or within the experimental domain, the capability to forecast the spatio-temporal evolution of plasma field…

等离子体物理 · 物理学 2023-02-14 Vignesh Gopakumar , Stanislas Pamela , Lorenzo Zanisi , Zongyi Li , Anima Anandkumar , MAST Team

Spectral bias, the tendency of neural networks to learn low-frequency features first, is a well-known issue with many training algorithms for physics-informed neural networks (PINNs). To overcome this issue, we propose IFeF-PINN, an…

机器学习 · 计算机科学 2025-10-23 Yulun Wu , Miguel Aguiar , Karl H. Johansson , Matthieu Barreau

In this paper, we propose a way to solve partial differential equations (PDEs) by combining machine learning techniques and the finite element method called Phi-FEM. For that, we use the Fourier Neural Operator (FNO), a learning mapping…

数值分析 · 数学 2025-03-05 Michel Duprez , Vanessa Lleras , Alexei Lozinski , Vincent Vigon , Killian Vuillemot