LTM: Large-scale Terrain Model for Wildfire-prone Landscapes

2026-07-09

AI Summary

This work addresses the challenge of generating high-fidelity terrain models in large-scale wildfire-prone regions, where conventional 3D reconstruction methods struggle due to sparse visual features, insufficient image overlap, or prohibitive costs. The authors propose a multimodal reconstruction framework that introduces a physics-informed, pixel-level alignment mechanism to directly register posed images with outdated digital elevation models (DEMs), bypassing computationally expensive feature matching and substantially reducing complexity. By fusing image-driven depth estimation with prior information from legacy DEMs, the method achieves significantly improved reconstruction accuracy and efficiency while maintaining real-time performance. Furthermore, the study develops a large-scale wildfire terrain simulator for training and evaluation, offering a scalable solution for high-fidelity terrain modeling to support wildfire emergency response.

Abstract

Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstruction methods underperform. Airborne LiDAR systems provide high-resolution terrain data, but they are expensive and infrequently updated. Image-based methods offer a lower-cost alternative, but struggle due to sparse visual features and limited image overlap. We propose a multi-modal reconstruction framework leveraging outdated Digital Elevation Models (DEMs) as geometric priors for image-based 3D reconstruction. Our key innovation is physics-based pixel-pixel alignment between images and DEM data, dramatically reducing computational complexity by eliminating expensive feature matching procedures. To validate our approach, we developed a large-terrain simulator based on a real wildfire-prone area, generating realistic images enabling a comprehensive evaluation. Given posed images and legacy DEMs, our method produces high-fidelity depth maps while maintaining real-time performance. We find significant improvements in reconstruction accuracy and computational efficiency over existing techniques, offering a scalable solution for wildfire response.

Problem

• wildfire-prone landscapes
• 3D terrain reconstruction
• large-scale terrain modeling
• Digital Elevation Models
• emergency response

Innovation

• multi-modal reconstruction
• physics-based alignment
• geometric priors
• real-time depth estimation
• wildfire terrain modeling