Semantic Stereo for Incidental Satellite Images
This work addresses the problem of reliable 3D mapping from multi-date satellite images for researchers, but it is incremental as it builds on existing methods and datasets.
The authors tackled the challenge of stereo reconstruction from incidental satellite images by introducing a large-scale public dataset with multi-view, multi-band images and ground truth labels for two cities, and they presented lightweight baselines adapted from state-of-the-art models to demonstrate the complementary nature of stereo and segmentation tasks.
The increasingly common use of incidental satellite images for stereo reconstruction versus rigidly tasked binocular or trinocular coincident collection is helping to enable timely global-scale 3D mapping; however, reliable stereo correspondence from multi-date image pairs remains very challenging due to seasonal appearance differences and scene change. Promising recent work suggests that semantic scene segmentation can provide a robust regularizing prior for resolving ambiguities in stereo correspondence and reconstruction problems. To enable research for pairwise semantic stereo and multi-view semantic 3D reconstruction with incidental satellite images, we have established a large-scale public dataset including multi-view, multi-band satellite images and ground truth geometric and semantic labels for two large cities. To demonstrate the complementary nature of the stereo and segmentation tasks, we present lightweight public baselines adapted from recent state of the art convolutional neural network models and assess their performance.