Saved in:
Bibliographic Details
Main Authors: Li, Zhihao, Dong, Shengwei, Yi, Chuang, Gao, Junxuan, Lai, Zhilu, Liu, Zhiqiang, Wang, Wei, Zhang, Guangtao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00149
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910035765886976
author Li, Zhihao
Dong, Shengwei
Yi, Chuang
Gao, Junxuan
Lai, Zhilu
Liu, Zhiqiang
Wang, Wei
Zhang, Guangtao
author_facet Li, Zhihao
Dong, Shengwei
Yi, Chuang
Gao, Junxuan
Lai, Zhilu
Liu, Zhiqiang
Wang, Wei
Zhang, Guangtao
contents Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-resolution (SR) with \textbf{ReMD} (\underline{Re}sidual-\underline{M}ultigrid \underline{D}iffusion), a physics-consistent diffusion framework. At each reverse step, ReMD performs a \emph{multigrid residual correction}: the update direction is obtained by coupling data consistency with lightweight physics cues and then correcting the residual across scales; the multiscale hierarchy is instantiated with a \emph{multi-wavelet} basis to capture both large structures and fine vortical details. This coarse-to-fine design accelerates convergence and preserves fine structures while remaining equation-free. Across atmospheric and oceanic benchmarks, ReMD improves accuracy and spectral fidelity, reduces divergence, and reaches comparable quality with markedly fewer sampling steps than diffusion baselines. Our results show that enforcing physics consistency \emph{inside} the diffusion process via multigrid residual correction and multi-wavelet multiscale modeling is an effective route to efficient fluid SR. Our code are available on https://github.com/lizhihao2022/ReMD.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00149
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction
Li, Zhihao
Dong, Shengwei
Yi, Chuang
Gao, Junxuan
Lai, Zhilu
Liu, Zhiqiang
Wang, Wei
Zhang, Guangtao
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-resolution (SR) with \textbf{ReMD} (\underline{Re}sidual-\underline{M}ultigrid \underline{D}iffusion), a physics-consistent diffusion framework. At each reverse step, ReMD performs a \emph{multigrid residual correction}: the update direction is obtained by coupling data consistency with lightweight physics cues and then correcting the residual across scales; the multiscale hierarchy is instantiated with a \emph{multi-wavelet} basis to capture both large structures and fine vortical details. This coarse-to-fine design accelerates convergence and preserves fine structures while remaining equation-free. Across atmospheric and oceanic benchmarks, ReMD improves accuracy and spectral fidelity, reduces divergence, and reaches comparable quality with markedly fewer sampling steps than diffusion baselines. Our results show that enforcing physics consistency \emph{inside} the diffusion process via multigrid residual correction and multi-wavelet multiscale modeling is an effective route to efficient fluid SR. Our code are available on https://github.com/lizhihao2022/ReMD.
title Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.00149