DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management
This work addresses the memory bottleneck for researchers and practitioners in 3D reconstruction and SLAM, enabling scalable applications in robotics and autonomous driving, though it is incremental in improving existing 3DGS SLAM frameworks.
The paper tackles the scalability limitation of 3D Gaussian Splatting (3DGS) in SLAM systems, which are constrained by GPU memory, by introducing DiskChunGS, a method that uses chunk-based memory management to enable large-scale reconstructions without memory failures, as validated on datasets like KITTI where it completed all 11 sequences with superior visual quality.
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.