中文
相关论文

相关论文: Probabilistic Physics-integrated Neural Differenti…

200 篇论文

Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feature space. However, they would produce severe artifacts in…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Chaohao Xie , Kai Han , Kwan-Yee K. Wong

Focused electron beam induced deposition (FEBID) is a powerful technique for 3D-printing of complex nanodevices. However, for resolutions below 10 nm, it struggles to control size, morphology and composition of the structures, due to a lack…

Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI remains challenging due to the ill-posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion…

We present a Physics-Informed Neural Network (PINN) to simulate the thermochemical evolution of a composite material on a tool undergoing cure in an autoclave. In particular, we solve the governing coupled system of differential equations…

机器学习 · 计算机科学 2021-06-16 Sina Amini Niaki , Ehsan Haghighat , Trevor Campbell , Anoush Poursartip , Reza Vaziri

Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal evolution of…

机器学习 · 计算机科学 2025-04-02 Adam P. Generale , Andreas E. Robertson , Surya R. Kalidindi

Vortex-induced vibrations (VIV) remain a canonical yet complex manifestation of fluid-structure interactions, where coupled nonlinear dynamics govern the motion of bluff bodies. For several years, we have relied on traditional reduced-order…

流体动力学 · 物理学 2026-03-31 Haimi Jha , Hibah Saddal , Chandan Bose

Flow-induced vibration (FIV) commonly occurs in rigidly coupled twin-pipe structures. However, the limited understanding of their FIV responses and hydrodynamic features presents a major challenge to the development of reliable engineering…

流体动力学 · 物理学 2025-06-09 Jiawei Shen , Shixiao Fu , Xuepeng Fu , Torgeir Moan , Svein Sævik

We present a novel characterization of mixing events associated with the propagation and overturning of internal waves, studied thanks to the simultaneous use of Particle Image Velocimetry (PIV) and Planar Laser Induced Fluorescence (PLIF)…

流体动力学 · 物理学 2021-02-10 Y. Dossmann , B. Bourget , C. Brouzet , T. Dauxois , S. Joubaud , P. Odier

Probabilistic modeling is iterative. A scientist posits a simple model, fits it to her data, refines it according to her analysis, and repeats. However, fitting complex models to large data is a bottleneck in this process. Deriving…

机器学习 · 统计学 2016-03-03 Alp Kucukelbir , Dustin Tran , Rajesh Ranganath , Andrew Gelman , David M. Blei

Given their increasing participation in fast-changing markets, the integration of scheduling and control is an important consideration in chemical process operations. This generally involves computing optimal production schedules using…

最优化与控制 · 数学 2020-05-19 Calvin Tsay , Michael Baldea

Vacuum Insulated Glazing (VIG) is a highly thermally insulating window technology, which boasts an extremely thin profile and lower weight as compared to gas-filled insulated glazing units of equivalent performance. The VIG is a double-pane…

计算机视觉与模式识别 · 计算机科学 2022-07-08 Henrik Riedel , Sleheddine Mokdad , Isabell Schulz , Cenk Kocer , Philipp Rosendahl , Jens Schneider , Michael A. Kraus , Michael Drass

Abdominal CT data are limited by high annotation costs and privacy constraints, which hinder the development of robust segmentation and diagnostic models. We present a Prior-Integrated Variation Modeling (PIVM) framework, a diffusion-based…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Dinglun He , Baoming Zhang , Xu Wang , Yao Hao , Deshan Yang , Ye Duan

Accurately predicting fluid dynamics and evolution has been a long-standing challenge in physical sciences. Conventional deep learning methods often rely on the nonlinear modeling capabilities of neural networks to establish mappings…

机器学习 · 计算机科学 2025-04-09 Huaguan Chen , Yang Liu , Hao Sun

A new gradient-based particle sampling method, MPM-ParVI, based on material point method (MPM), is proposed for variational inference. MPM-ParVI simulates the deformation of a deformable body (e.g. a solid or fluid) under external effects…

人工智能 · 计算机科学 2024-07-31 Yongchao Huang

Infrared-visible image fusion (IVIF) has attracted much attention owing to the highly-complementary properties of the two image modalities. Due to the lack of ground-truth fused images, the fusion output of current deep-learning based…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Yuhao Wang , Lingjuan Miao , Zhiqiang Zhou , Lei Zhang , Yajun Qiao

Computer models play a crucial role in numerous scientific and engineering domains. To ensure the accuracy of simulations, it is essential to properly calibrate the input parameters of these models through statistical inference. While…

应用统计 · 统计学 2024-03-07 Dongkyu Derek Cho , Won Chang , Jaewoo Park

This work introduces the conditioned Vehicle Motion Diffusion (cVMD) model, a novel network architecture for highway trajectory prediction using diffusion models. The proposed model ensures the drivability of the predicted trajectory by…

机器学习 · 计算机科学 2024-05-24 Marion Neumeier , Sebastian Dorn , Michael Botsch , Wolfgang Utschick

The zeolitic imidazolate frameworks (ZIF) have emerged as a promising candidate for catalysis, carbon-dioxide (CO$_{2}$) capture and storage as well as flue gas separation due to their tunable porosity and chemical stability. ZIFs consists…

材料科学 · 物理学 2025-04-10 Michael O. Atambo , Korir Kiptiemoi

Particle image velocimetry (PIV) is essential in experimental fluid dynamics. In the current work, we propose a new velocity field estimation paradigm, which achieves a synergetic combination of the deep learning method and the traditional…

流体动力学 · 物理学 2022-01-12 Qi Gao , Hongtao Lin , Han Tu , Haoran Zhu , Runjie Wei , Guoping Zhang , Xueming Shao

Neural networks offer powerful tools to solve partial differential equations (PDEs). We present a Variational Physics-Informed Neural Network (VPINN) designed for parabolic problems. Our approach combines a classical time discretization…