Abstract:Scientific measurements are often bottlenecked by suboptimal conditions, whether that be noise, incomplete spatial coverage, or limited resolution, rendering accurate field reconstruction a difficult task. We introduce LatentPDE, a latent diffusion framework designed to simultaneously resolve sparse-observation reconstruction and super-resolution. While existing physics-guided diffusion models typically rely on soft loss penalties or uninterpretable representations, our approach enforces physical compliance by constructing an inherently interpretable latent space. Specifically, we parameterize the latent variables directly as the coefficients and source terms of an assumed governing PDE. In doing so, LatentPDE is able to reliably reconstruct dynamics across highly disparate and structured data gaps. Empirical results on diverse configurations demonstrate that our model achieves high-fidelity recovery at any desired resolution while also tracking the underlying predictive uncertainty.
| Comments: | 28 pages, 20 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.23867 [cs.LG] |
| (or arXiv:2604.23867v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.23867 arXiv-issued DOI via DataCite (pending registration) |
From: Valerie Tsao [view email]
[v1]
Sun, 26 Apr 2026 20:14:17 UTC (8,323 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。