AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model

2026-03-05

AI Summary

This work addresses the limitations of dense reconstruction in monocular visual SLAM, which often stems from suboptimal multi-view selection strategies that inadequately exploit geometric context—typically restricted to a fixed number of views or pairwise two-view configurations. To overcome this, we propose AIM-SLAM, a novel framework featuring the SIGMA module that adaptively selects keyframes based on voxel overlap and information gain. For the first time, geometric-aware multi-view joint Sim(3) optimization is integrated into the monocular dense SLAM pipeline. Coupled with a Visual Geometry Foundation Model (VGGT) for dense point map prediction, our approach achieves state-of-the-art performance in both pose estimation and reconstruction accuracy on real-world datasets, while also supporting deployment within the ROS ecosystem.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent advances in geometric foundation models have emerged as a promising alternative for addressing the challenge of dense reconstruction in monocular visual simultaneous localization and mapping (SLAM). Although geometric foundation models enable SLAM to leverage variable input views, the previous methods remain confined to two-view pairs or fixed-length inputs without sufficient deliberation of geometric context for view selection. To tackle this problem, we propose AIM-SLAM, a dense monocular SLAM framework that exploits an adaptive and informative multi-view keyframe prioritization with dense pointmap predictions from visual geometry grounded transformer (VGGT). Specifically, we introduce the selective information- and geometric-aware multi-view adaptation (SIGMA) module, which employs voxel overlap and information gain to retrieve a candidate set of keyframes and adaptively determine its size. Furthermore, we formulate a joint multi-view Sim(3) optimization that enforces consistent alignment across selected views, substantially improving pose estimation accuracy. The effectiveness of AIM-SLAM is demonstrated on real-world datasets, where it achieves state-of-the-art performance in both pose estimation and dense reconstruction. Our system supports ROS integration, with code is available at https://aimslam.github.io/.

Problem

• monocular SLAM
• dense reconstruction
• geometric foundation models
• multi-view selection
• keyframe prioritization

Innovation

• multi-view keyframe prioritization
• adaptive selection
• geometric foundation model
• dense reconstruction
• Sim(3) optimization