Learning Dense Stereo Matching for Digital Surface Models from Satellite Imagery

2018/11/08 by Wayne Treible, Scott Sorensen, Treible, Wayne +7
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics and Sensor-Based Localization #Satellite Image Processing and Photogrammetry

paper · pdf · doi:10.48550/arxiv.1811.03535

openalex publication_date 2018/11/08 · openalex created_date 2018/11/16 · openalex updated_date 2026/07/28

Abstract

Digital Surface Model generation from satellite imagery is a difficult task that has been largely overlooked by the deep learning community. Stereo reconstruction techniques developed for terrestrial systems including self driving cars do not translate well to satellite imagery where image pairs vary considerably. In this work we present neural network tailored for Digital Surface Model generation, a ground truthing and training scheme which maximizes available hardware, and we present a comparison to existing methods. The resulting models are smooth, preserve boundaries, and enable further processing. This represents one of the first attempts at leveraging deep learning in this domain.

Citations

• Pyramid Stereo Matching Network
• Learning to Compare Image Patches via Convolutional Neural Networks
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• Aggregated Residual Transformations for Deep Neural Networks

Related

• Deep Learning Meets Satellite Images -- An Evaluation on Handcrafted and Learning-based Features for Multi-date Satellite Stereo Images
• Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision
• Fine-tuning deep learning models for stereo matching using results from semi-global matching
• DeepSim-Nets: Deep Similarity Networks for Stereo Image Matching
• SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images