MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representations

arXiv:2403.17765v1 Announce Type: new
Abstract: We introduce MUTE-SLAM, a real-time neural RGB-D SLAM system employing multiple tri-plane hash-encodings for efficient scene representation. MUTE-SLAM effectively tracks camera positions and incrementally builds a scalable multi-map representation for both small and large indoor environments. It dynamically allocates sub-maps for newly observed local regions, enabling constraint-free mapping without prior scene information. Unlike traditional grid-based methods, we use three orthogonal axis-aligned planes for hash-encoding scene properties, significantly reducing hash collisions and the number of trainable …

abstract arxiv cs.cv enabling environments hash map maps multiple plane real-time representation rgb-d scalable slam small type