Spatial-temporal switching estimators for imaging locally concentrated dynamics
This work addresses real-time image reconstruction for physics-based dynamics like cloud monitoring, but it appears incremental as it builds on existing SLDS models with patch-based methods.
The paper tackled the problem of reconstructing images with locally concentrated, nonlinear dynamics by proposing patch-based hybrid estimators for a switching linear dynamic system (SLDS), demonstrating effectiveness in denoising remotely sensed cloud dynamics through numerical simulations.
The evolution of images with physics-based dynamics is often spatially localized and nonlinear. A switching linear dynamic system (SLDS) is a natural model under which to pose such problems when the system's evolution randomly switches over the observation interval. Because of the high parameter space dimensionality, efficient and accurate recovery of the underlying state is challenging. The work presented in this paper focuses on the common cases where the dynamic evolution may be adequately modeled as a collection of decoupled, locally concentrated dynamic operators. Patch-based hybrid estimators are proposed for real-time reconstruction of images from noisy measurements given perfect or partial information about the underlying system dynamics. Numerical results demonstrate the effectiveness of the proposed approach for denoising in a realistic data-driven simulation of remotely sensed cloud dynamics.