RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

TL;DR

RADIO-ViPE is an online semantic SLAM system that integrates vision and language embeddings with geometric data from monocular RGB videos, enabling open-vocabulary scene understanding in dynamic environments without prior calibration.

Contribution

It introduces a tightly coupled multi-modal fusion approach that operates directly on raw RGB video, handling dynamic scenes and moving objects without requiring calibration or depth sensors.

Findings

Achieves state-of-the-art results on the dynamic TUM-RGBD benchmark.

Maintains competitive performance against offline methods with static scene assumptions.

Operates effectively in real-world, unconstrained environments.

Abstract

We present RADIO-ViPE (Reduce All Domains Into One -- Video Pose Engine), an online semantic SLAM system that enables geometry-aware open-vocabulary grounding, associating arbitrary natural language queries with localized 3D regions and objects in dynamic environments. Unlike existing approaches that require calibrated, posed RGB-D input, RADIO-ViPE operates directly on raw monocular RGB video streams, requiring no prior camera intrinsics, depth sensors, or pose initialization. The system tightly couples multi-modal embeddings -- spanning vision and language -- derived from agglomerative foundation models (e.g., RADIO) with geometric scene information. This coupling takes place in initialization, optimization and factor graph connections to improve the consistency of the map from multiple modalities. The optimization is wrapped within adaptive robust kernels, designed to handle both actively moving objects and agent-displaced scene elements (e.g., furniture rearranged during ego-centric session). Experiments demonstrate that RADIO-ViPE achieves state-of-the-art results on the dynamic TUM-RGBD benchmark while maintaining competitive performance against offline open-vocabulary methods that rely on calibrated data and static scene assumptions. RADIO-ViPE bridges a critical gap in real-world deployment, enabling robust open-vocabulary semantic grounding for autonomous robotics and unconstrained in-the-wild video streams. Project page: https://be2rlab.github.io/radio_vipe