AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model
For SLAM researchers, this work addresses the bottleneck of view selection in multi-view dense monocular SLAM by introducing an adaptive and informative keyframe prioritization method.
AIM-SLAM proposes a dense monocular SLAM framework using adaptive multi-view keyframe selection with geometric foundation models, achieving state-of-the-art pose estimation and accurate dense reconstruction on real-world datasets.
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 pose estimation performance and accurate dense reconstruction results. Our system supports ROS integration, with code is available at https://aimslam.github.io/.