English
Related papers

Related papers: An efficient diffusion generated motion method for…

200 papers

How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Binxu Wang , John J. Vastola

State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Andrey Voynov , Amir Hertz , Moab Arar , Shlomi Fruchter , Daniel Cohen-Or

Statistical surrogate modeling of fluid flows is hard because dynamics are multiscale and highly sensitive to initial conditions. Conditional diffusion surrogates can be accurate, but usually need hundreds of stochastic sampling steps. We…

Machine Learning · Computer Science 2026-02-10 Victor Armegioiu , Yannick Ramic , Siddhartha Mishra

When comparing measurements to numerical simulations of moisture transfer through porous materials a rush of the experimental moisture front is commonly observed in several works shown in the literature, with transient models that consider…

Computational Engineering, Finance, and Science · Computer Science 2020-02-20 Julien Berger , Suelen Gasparin , Denys Dutykh , Nathan Mendes

The time-fractional diffusion equation is considered, where the time derivative is either of Caputo or Riemann-Liouville type. The solution of a general initial-boundary value problem with time-dependent boundary conditions over bounded and…

Analysis of PDEs · Mathematics 2023-01-04 M. Rodrigo

This paper presents a three-dimensional framework for simulating dynamic wetting phenomena using the volume of fluid (VOF) method, implemented in Basilisk. A geometric interpolation scheme is developed to obtain an accurate and reliable…

Fluid Dynamics · Physics 2025-09-26 Yifan Han , Gerd Mutschke , Kerstin Eckert

DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging selected points. The method claims that accurate spatial control can be achieved by optimizing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Ali Subhan , Ashir Raza

We simulate the mesoscopic dynamics of droplets formed by phase separated fluids at nanometer scales where thermal fluctuations are significant. Both spherical droplets fully immersed in a second fluid and sessile droplets which are also in…

Fluid Dynamics · Physics 2024-11-18 John B. Bell , Andrew Nonaka , Alejandro L. Garcia

Dewetting of liquid films on solid surfaces in the presence of evaporation is a common phenomenon and has been studied by many researchers. The previous numerical approach has revealed that evaporation accelerates the dewetting speed of the…

Soft Condensed Matter · Physics 2023-05-16 Xiaolong Zhang , Vadim Nikolayev

Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Yushan Zhang , Bastian Wandt , Maria Magnusson , Michael Felsberg

Recent advances in data-driven modeling have shown that diffusion models can successfully generate synthetic Lagrangian trajectories in turbulent flows. Building on this progress, we extend the method to the joint generation of pairs of…

Diffusion models have revolutionized various application domains, including computer vision and audio generation. Despite the state-of-the-art performance, diffusion models are known for their slow sample generation due to the extensive…

Machine Learning · Computer Science 2024-06-25 Zehao Dou , Minshuo Chen , Mengdi Wang , Zhuoran Yang

We present the detailed analysis of the diffusive transport of spatially inhomogeneous fluid mixtures and the interplay between structural and dynamical properties varying on the atomic scale. The present treatment is based on different…

Mesoscale and Nanoscale Physics · Physics 2011-05-19 Umberto Marini Bettolo Marconi , Simone Melchionna

We briefly discuss how the wetting properties of a fluid/solid interface can indirectly influence the diffusion properties of fluid confined between two solid walls. This influence is related to the variability of the hydrodynamic boundary…

Soft Condensed Matter · Physics 2007-05-23 Yannick Alméras , Jean-Louis Barrat , Lydéric Bocquet

We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore…

Fluid Dynamics · Physics 2026-02-23 Noah Trupin , Rahul Ghosh , Aadi Jangid

This work presents a detailed mathematical model combined with an innovative efficient numerical model to predict heat, air and moisture transfer through porous building materials. The model considers the transient effects of air transport…

Applied Physics · Physics 2020-02-20 Julien Berger , Denys Dutykh , Nathan Mendes , Bolatbek Rysbaiuly

The vaporization of a freely moving drop in a uniform, high-temperature gas stream is investigated through direct numerical simulation. The incompressible Navier-Stokes equations with surface tension and phase change are solved in…

Fluid Dynamics · Physics 2023-10-03 Bradley Boyd , Sid Becker , Yue Ling

Score-based generative models are shown to achieve remarkable empirical performances in various applications such as image generation and audio synthesis. However, a theoretical understanding of score-based diffusion models is still…

Machine Learning · Computer Science 2022-12-14 Dohyun Kwon , Ying Fan , Kangwook Lee

We explicitly solve the optimal switching problem for one-dimensional diffusions by directly employing the dynamic programming principle and the excessive characterization of the value function. The shape of the value function and the…

Optimization and Control · Mathematics 2009-05-25 Erhan Bayraktar , Masahiko Egami

Score-based methods have recently seen increasing popularity in modeling and generation. Methods have been constructed to perform hypothesis testing and change-point detection with score functions, but these methods are in general not as…

Machine Learning · Statistics 2025-06-23 Sean Moushegian , Taposh Banerjee , Vahid Tarokh
‹ Prev 1 8 9 10 Next ›