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

TL;DR

Mono-Hydra++ is a real-time monocular RGB-IMU system that constructs 3D indoor scene graphs, enabling semantic understanding for lightweight robots without active depth sensors.

Contribution

It introduces a novel multi-task deep model and a pipeline for real-time semantic mapping and scene graph construction using only monocular RGB and IMU data.

Findings

Achieves 1.6% lower trajectory error than RGB-D baseline on ScanNet

Improves average ATE by 29.8% over calibrated baselines on 7-Scenes

Runs at 25.53 FPS on Jetson Orin NX with embedded perception model

Abstract

Autonomous agile robots need more than metric geometry: they must understand objects, rooms, places, and spatial relations for search, inspection, exploration, and human robot interaction. Conventional metric maps support 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. Building such representations on agile platforms remains difficult because aerial and lightweight robots operate under strict payload, power, and compute limits, making RGB-D cameras and LiDAR sensors impractical for many onboard settings. We present Mono-Hydra++, a real time monocular RGB plus IMU pipeline for indoor metric semantic mapping and hierarchical 3D scene graph construction. The system combines M2H-MX, a DINOv3 based multi-task model for depth and semantics, with a deep feature visual inertial odometry front end, sparse predicted depth constraints in the VIO derived pose graph, semantic masking for dynamic regions, and pose aware temporal alignment before volumetric fusion in the Mono-Hydra backend. On the Go-SLAM ScanNet evaluation subset, Mono-Hydra++ achieves 1.6% lower average trajectory error than the strongest RGB-D baseline in our comparison, while using only monocular RGB plus IMU input. On calibrated 7-Scenes, it improves average ATE by 29.8% over the strongest competing calibrated baseline. We further validate Mono-Hydra++ in a real ITC building deployment using RealSense RGB plus IMU and demonstrate embedded feasibility by deploying the ONNX/TensorRT FP16 M2H-MX-L perception model at 25.53 FPS on a Jetson Orin NX 16GB. These results show that Mono-Hydra++ can provide real time metric semantic mapping and scene graph construction for resource constrained robotic platforms without relying on active depth sensors.