SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos
In this paper, we introduce SLAM3R, a novel and effective monocular RGB SLAM system for real-time and high-quality dense 3D reconstruction. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based 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 and weights at: https://github.com/PKU-VCL-3DV/SLAM3R.
Code (1)
Tasks
3D ReconstructionSimilar Papers 제목 키워드 기반
DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM System
We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and…
Simultaneous Localization and MappingMoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applica…
3D Reconstruction3D Scene ReconstructionDepth EstimationLoop Closure Detection+4SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors
Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time per…
Simultaneous Localization and MappingSurface ReconstructionSplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting
Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene …
3DGS3D ReconstructionNeRFSSIMGRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State
DUSt3R-based end-to-end scene reconstruction has recently shown promising results in dense visual SLAM. However, most existing methods only use image pairs to estimate pointmaps, overlooking spatial memory and global con…
Pose EstimationPoint Clouds