NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
This addresses the challenge of accurate dense mapping and tracking in visual SLAM for robotics or AR/VR applications, though it is incremental as it builds on existing neural implicit SLAM methods.
The paper tackles the problem of dense RGB SLAM without relying on depth sensors, presenting NICER-SLAM which simultaneously optimizes camera poses and a neural implicit map for high-fidelity 3D reconstruction and novel view synthesis, achieving performance competitive with RGB-D SLAM systems on synthetic and real-world datasets.
Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, previous works in this direction either rely on RGB-D sensors, or require a separate monocular SLAM approach for camera tracking and do not produce high-fidelity dense 3D scene reconstruction. In this paper, we present NICER-SLAM, a dense RGB SLAM system that simultaneously optimizes for camera poses and a hierarchical neural implicit map representation, which also allows for high-quality novel view synthesis. To facilitate the optimization process for mapping, we integrate additional supervision signals including easy-to-obtain monocular geometric cues and optical flow, and also introduce a simple warping loss to further enforce geometry consistency. Moreover, to further boost performance in complicated indoor scenes, we also propose a local adaptive transformation from signed distance functions (SDFs) to density in the volume rendering equation. On both synthetic and real-world datasets we demonstrate strong performance in dense mapping, tracking, and novel view synthesis, even competitive with recent RGB-D SLAM systems.