PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM

TL;DR

PointSLAM++ is a neural Gaussian-based SLAM system that improves real-time 3D mapping accuracy and robustness in noisy environments by using hierarchical constraints, dynamic adaptation, and progressive pose optimization.

Contribution

It introduces a novel neural Gaussian representation with hierarchical constraints and dynamic adaptation for improved dense SLAM performance.

Findings

Outperforms existing 3DGS SLAM methods in accuracy

Provides high-quality photorealistic scene rendering

Enhances robustness to depth sensor noise

Abstract

Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D SLAM system that leverages a hierarchically constrained neural Gaussian representation to preserve structural relationships while generating Gaussian primitives for scene mapping. It also employs progressive pose optimization to mitigate depth sensor noise, significantly enhancing localization accuracy. Furthermore, it utilizes a dynamic neural representation graph that adjusts the distribution of Gaussian nodes based on local geometric complexity, enabling the map to adapt to intricate scene details in real time. This combination yields high-precision 3D mapping and photorealistic scene rendering. Experimental results show PointSLAM++ outperforms existing 3DGS-based SLAM methods in reconstruction accuracy and rendering quality, demonstrating its advantages for large-scale AR and robotics.