Passage-Aware Structural Mapping for RGB-D Visual SLAM

TL;DR

This paper introduces a passage-aware structural mapping method for RGB-D VSLAM that detects doors and passages by combining geometric, semantic, and topological cues, enhancing indoor navigation and scene understanding.

Contribution

It presents a novel approach to detect and model doors and passages within VSLAM by integrating geometric, semantic, and topological information, and demonstrates its integration into vS-Graphs.

Findings

Reliable doorway detection in indoor sequences

Enhanced scene graph with passage-level abstractions

Improved room connectivity modeling

Abstract

Doorways and passages are critical structural elements for indoor robot navigation, yet they remain underexplored in modern Visual SLAM (VSLAM) frameworks. This paper presents a passage-aware structural mapping approach for RGB-D VSLAM that detects doors and traversable openings by jointly fusing geometric, semantic, and topological cues. Doors are modeled as planar entities embedded within walls and classified as traversable or non-traversable based on their coplanarity with the supporting wall. Passages are inferred through two complementary strategies: traversal evidence accumulated from camera-wall interactions across consecutive keyframes, and geometric opening validation based on discontinuities in the mapped wall geometry. The proposed method is integrated into vS-Graphs as a proof of concept, enriching its scene graph with passage-level abstractions and improving room connectivity modeling. Qualitative evaluations on indoor office sequences demonstrate reliable doorway detection, and the framework lays the foundation for exploiting these elements in BIM-informed VSLAM. The source code is publicly available at https://github.com/snt-arg/visual_sgraphs/tree/doorway_integration.