Dfilled: Repurposing Edge-Enhancing Diffusion for Guided DSM Void Filling

2025-01-26

AI Summary

Digital surface models (DSMs) derived from satellite stereo imagery often suffer from voids and elevation distortions—particularly in occluded or shadowed terrain—leading to geometric discontinuities. To address this, we propose an optical remote sensing image-guided edge-enhanced diffusion inpainting method. First, we adapt an anisotropic diffusion model—originally designed for super-resolution—to DSM void filling. Second, we introduce Perlin noise to generate structurally aware, semantically consistent void masks. Third, we jointly leverage multi-scale edge features and optical image priors to achieve geometry-semantic co-regularized reconstruction. Experiments demonstrate that our method significantly outperforms conventional interpolation and state-of-the-art deep learning approaches in terms of RMSE and SSIM. Notably, it substantially improves elevation accuracy and surface continuity over complex land cover types—including buildings and vegetation—while preserving fine-scale topographic structures.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Mixed Discrete/Continuous Search
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Digital Surface Models (DSMs) are essential for accurately representing Earth's topography in geospatial analyses. DSMs capture detailed elevations of natural and manmade features, crucial for applications like urban planning, vegetation studies, and 3D reconstruction. However, DSMs derived from stereo satellite imagery often contain voids or missing data due to occlusions, shadows, and lowsignal areas. Previous studies have primarily focused on void filling for digital elevation models (DEMs) and Digital Terrain Models (DTMs), employing methods such as inverse distance weighting (IDW), kriging, and spline interpolation. While effective for simpler terrains, these approaches often fail to handle the intricate structures present in DSMs. To overcome these limitations, we introduce Dfilled, a guided DSM void filling method that leverages optical remote sensing images through edge-enhancing diffusion. Dfilled repurposes deep anisotropic diffusion models, which originally designed for super-resolution tasks, to inpaint DSMs. Additionally, we utilize Perlin noise to create inpainting masks that mimic natural void patterns in DSMs. Experimental evaluations demonstrate that Dfilled surpasses traditional interpolation methods and deep learning approaches in DSM void filling tasks. Both quantitative and qualitative assessments highlight the method's ability to manage complex features and deliver accurate, visually coherent results.

Problem

• Digital Surface Models
• Data Loss
• Complex Terrain

Innovation

• Dfilled
• Edge Enhancement
• Optical Remote Sensing