IRIS-SLAM: Unified Geo-Instance Representations for Robust Semantic Localization and Mapping

TL;DR

IRIS-SLAM introduces a unified semantic and geometric RGB SLAM system using foundation models to improve map consistency and loop closure robustness.

Contribution

It extends geometry foundation models to predict dense geometry and semantic embeddings simultaneously, enabling better data association and loop closure detection.

Findings

Outperforms state-of-the-art methods in map consistency.

Enhances wide-baseline loop closure reliability.

Effectively utilizes viewpoint-agnostic semantic anchors.

Abstract

Geometry foundation models have significantly advanced dense geometric SLAM, yet existing systems often lack deep semantic understanding and robust loop closure capabilities. Meanwhile, contemporary semantic mapping approaches are frequently hindered by decoupled architectures and fragile data association. We propose IRIS-SLAM, a novel RGB semantic SLAM system that leverages unified geometric-instance representations derived from an instance-extended foundation model. By extending a geometry foundation model to concurrently predict dense geometry and cross-view consistent instance embeddings, we enable a semantic-synergized association mechanism and instance-guided loop closure detection. Our approach effectively utilizes viewpoint-agnostic semantic anchors to bridge the gap between geometric reconstruction and open-vocabulary mapping. Experimental results demonstrate that IRIS-SLAM significantly outperforms state-of-the-art methods, particularly in map consistency and wide-baseline loop closure reliability.