English
Related papers

Related papers: Inverting the Ray-Knight identity on the line

200 papers

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Rui Zhu , Yingwei Pan , Yehao Li , Ting Yao , Zhenglong Sun , Tao Mei , Chang Wen Chen

This paper develops a novel approach to the problem of source current identification for the diffusion equation in connection with geophysical self-potential measurements. The problem is split into two subproblems: (a) the scalar source…

Geophysics · Physics 2019-01-15 Mikhail Malovichko , Nikolay Yavich

In this paper, we explain the convergence speed of different iteration schemes with the fluid diffusion view when solving a linear fixed point problem. This interpretation allows one to better understand why power iteration or Jacobi…

Numerical Analysis · Computer Science 2013-04-08 Dohy Hong

Due to some complex factors (e.g., occlusion, pose variation and diverse camera perspectives), extracting stronger feature representation in person re-identification remains a challenging task. In this paper, we proposed a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Zhangjian Ji , Donglin Cheng , Kai Feng

We develop an encounter-based approach for describing restricted diffusion with a gradient drift towards a partially reactive boundary. For this purpose, we introduce an extension of the Dirichlet-to-Neumann operator and use its eigenbasis…

Chemical Physics · Physics 2022-10-10 Denis S. Grebenkov

Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Yan Huang , Qiang Wu , JingSong Xu , Yi Zhong

In this paper, we propose a new adaptation of the D-iteration algorithm to numerically solve the differential equations. This problem can be reinterpreted in 2D or 3D (or higher dimensions) as a limit of a diffusion process where the…

Numerical Analysis · Computer Science 2012-04-30 Dohy Hong

In this article we study inverse problems of recovering a space-time dependent source component from the lateral boundary observation in a subidffusion model. The mathematical model involves a Djrbashian-Caputo fractional derivative of…

Numerical Analysis · Mathematics 2021-05-19 Bangti Jin , Yavar Kian , Zhi Zhou

Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Linjie Lyu , Ayush Tewari , Marc Habermann , Shunsuke Saito , Michael Zollhöfer , Thomas Leimkühler , Christian Theobalt

The problem of reconstructing the time dependence of the dynamic pressure of a plasma jet impinging on one end of a solid rod based on the measured displacement of the opposite end has been solved. This solution allows for a reduction in…

Plasma Physics · Physics 2025-11-12 Evgeny Kolesnikov , Igor Kotelnikov , Vadim Prikhodko

Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade re-ID performance in…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Yu-Jhe Li , Yun-Chun Chen , Yen-Yu Lin , Yu-Chiang Frank Wang

In the context of incompressible fluids, the observation that turbulent singular structures fail to be space filling is known as ``intermittency'' and it has strong experimental foundations. Consequently, as first pointed out by Landau,…

Analysis of PDEs · Mathematics 2023-12-19 Luigi De Rosa , Philip Isett

Machine learning methods, such as diffusion models, are widely explored as a promising way to accelerate high-fidelity fluid dynamics computation via a super-resolution process from faster-to-compute low-fidelity input. However, existing…

Computational Engineering, Finance, and Science · Computer Science 2025-12-24 Ruoyan Li , Zijie Huang , Haixin Wang , Guancheng Wan , Yizhou Sun , Wei Wang

In this study, singular diffusion operator with jump conditions is considered. Integral representations have been derived for solutions that satisfy boundary conditions and jump conditions. Some properties of eigenvalues and eigenfunctions…

Spectral Theory · Mathematics 2020-06-25 Abdullah Ergün

Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsupervised Re-Id are mostly based on the method alternating…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 De Cheng , Jingyu Zhou , Nannan Wang , Xinbo Gao

This paper explores the reconstruction of drift or diffusion coefficients of a scalar stochastic diffusion processes as it starts from an initial value and reaches, for the first time, a threshold value. We show that the distribution…

Statistical Mechanics · Physics 2009-11-10 Guillaume Bal , Tom Chou

We present an integral of diffraction based on particular eigenfunctions of the Laplacian in two dimensions. We show how to propagate some fields, in particular a Bessel field, a superposition of Airy beams, both over the square root of the…

We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward…

Machine Learning · Computer Science 2025-12-09 Guanxiong Luo , Shoujin Huang , Yanlong Yang

We present a concise, self-contained derivation of diffusion-based generative models. Starting from basic properties of Gaussian distributions (densities, quadratic expectations, re-parameterisation, products, and KL divergences), we…

Machine Learning · Computer Science 2025-11-18 Sepehr Maleki , Negar Pourmoazemi

Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due to the numerous sampling iterations required. To accelerate…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Kexun Zhang , Xianjun Yang , William Yang Wang , Lei Li
‹ Prev 1 3 4 5 6 7 10 Next ›