SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an endto-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feedforward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimizationbased methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a globally consistent scene reconstruction -all without explicitly solving any camera parameters. Experiments across datasets consistently show that SLAM3R achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS. Code available at: https://github.com/PKU-VCL-3DV/SLAM3R .