DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management

TL;DR

DiskChunGS introduces a scalable 3D Gaussian SLAM system that manages large scenes efficiently by using chunk-based memory management, enabling real-time, large-scale 3D reconstruction without GPU memory limitations.

Contribution

It presents a novel out-of-core approach for 3D Gaussian SLAM that handles scene data in chunks, overcoming GPU memory constraints and enabling large-scale, real-time SLAM.

Findings

Successfully completes all KITTI sequences without memory failures.

Achieves superior visual quality compared to previous methods.

Operates effectively on resource-constrained platforms like Nvidia Jetson.

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results for novel view synthesis with real-time rendering capabilities. However, integrating 3DGS with SLAM systems faces a fundamental scalability limitation: methods are constrained by GPU memory capacity, restricting reconstruction to small-scale environments. We present DiskChunGS, a scalable 3DGS SLAM system that overcomes this bottleneck through an out-of-core approach that partitions scenes into spatial chunks and maintains only active regions in GPU memory while storing inactive areas on disk. Our architecture integrates seamlessly with existing SLAM frameworks for pose estimation and loop closure, enabling globally consistent reconstruction at scale. We validate DiskChunGS on indoor scenes (Replica, TUM-RGBD), urban driving scenarios (KITTI), and resource-constrained Nvidia Jetson platforms. Our method uniquely completes all 11 KITTI sequences without memory failures while achieving superior visual quality, demonstrating that algorithmic innovation can overcome the memory constraints that have limited previous 3DGS SLAM methods.