Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping

ArXi:2605.17661v1 Announce Type: cross Autonomous agile robots need than metric geometry: they must understand objects, rooms, places, and spatial relations for search, inspection, exploration, and human robot interaction. Conventional metric maps localization and collision avoidance, but do not provide this semantic and relational structure. 3D scene graphs address this gap by connecting geometry with object level and room level understanding.