Efficient Terrain Stochastic Differential Efficient Terrain Stochastic Differential Equations for Multipurpose Digital Elevation Model Restoration

TL;DR

This paper introduces ET-SDE, a unified stochastic differential equation model that enhances digital elevation models across multiple tasks, offering improved quality, faster inference, and better generalization compared to existing methods.

Contribution

The paper proposes a novel, unified SDE-based framework for multipurpose DEM restoration, diverging from task-specific methods and incorporating efficient modules for superior performance.

Findings

Achieves state-of-the-art results in super-resolution, void filling, and denoising.

Demonstrates faster inference speeds than existing methods.

Generalizes effectively across various DEM restoration tasks.

Abstract

Digital Elevation Models (DEMs) are indispensable in the fields of remote sensing and photogrammetry, with their refinement and enhancement being critical for a diverse array of applications. Numerous methods have been developed for enhancing DEMs, but most of them concentrate on tackling specific tasks individually. This paper presents a unified generative model for multipurpose DEM restoration, diverging from the conventional approach that typically targets isolated tasks. We modify the mean-reverting stochastic differential equation, to generally refine the DEMs by conditioning on the learned terrain priors. The proposed Efficient Terrain Stochastic Differential Equation (ET-SDE) models DEM degradation through SDE progression and restores it via a simulated reversal process. Leveraging efficient submodules with lightweight channel attention, this adapted SDE boosts DEM quality and streamlines the training process. The experiments show that ET-SDE achieves highly competitive restoration performance on super-resolution, void filling, denoising, and their combinations, compared to the state-of-the-art work. In addition to its restoration capabilities, ET-SDE also demonstrates faster inference speeds and the capacity to generalize across various tasks, particularly for larger patches of DEMs.