GeoDecoder: Empowering Multimodal Map Understanding

arXiv:2401.15118v2 Announce Type: replace
Abstract: This paper presents GeoDecoder, a dedicated multimodal model designed for processing geospatial information in maps. Built on the BeitGPT architecture, GeoDecoder incorporates specialized expert modules for image and text processing. On the image side, GeoDecoder utilizes GaoDe Amap as the underlying base map, which inherently encompasses essential details about road and building shapes, relative positions, and other attributes. Through the utilization of rendering techniques, the model seamlessly integrates external data and features such as symbol …

abstract architecture arxiv cs.ai cs.cv expert geospatial image information map maps modules multimodal multimodal model paper processing text type understanding