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

Why It Matters

It enables real‑time, high‑resolution 3D mapping on low‑power hardware, unlocking advanced SLAM capabilities for mobile robots and edge devices.

Key Takeaways

• Chunk-based memory lets 3D Gaussian SLAM exceed GPU limits
• Active scene regions streamed to VRAM while inactive stored on disk
• Key‑frame depth estimation directly places Gaussians from image content
• Method runs on Jetson, enabling real‑time SLAM for mobile robots
• Visual comparisons show sharper detail than state‑of‑the‑art methods

Summary

DiskChunGS introduces a scalable 3D Gaussian splatting SLAM pipeline that overcomes traditional GPU memory constraints by treating scene reconstruction as a spatial streaming problem. The system partitions the environment into discrete chunks, keeping only the currently visible regions in GPU VRAM while offloading inactive chunks to disk, enabling reconstruction of extensive trajectories without hardware scaling.

The pipeline estimates depth for each SLAM key frame and directly places Gaussian primitives based on image content. Frustum‑based color culling identifies which chunks to load, and old chunks are evicted back to disk. Visible Gaussians are rasterized, losses computed, and gradients back‑propagated to refine parameters, delivering high‑fidelity reconstructions across challenging datasets such as Kitty, Replica, and TUM, even with multiple loop closures.

Demonstrations include visual comparisons that highlight clearer detail than competing methods, and a Ross wrapper that accepts external pose inputs for seamless integration with existing SLAM systems. The authors also showcase real‑time performance on the resource‑constrained NVIDIA Jetson platform and on the Grand Tour dataset using logged onboard poses and RGB‑D data.

By decoupling scene size from GPU capacity, DiskChunGS makes large‑scale, high‑quality SLAM feasible for mobile robotics, AR/VR, and autonomous navigation, expanding the operational envelope of devices that previously struggled with memory‑bound reconstruction.

Original Description

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

Paper Link: https://www.arxiv.org/abs/2511.23030

Website Link: https://rffr.leggedrobotics.com/works/diskchungs/

Authors: Casimir Feldmann, Maximum Wilder-Smith, Vaishakh Patil, Michael Oechsle, Michael Niemeyer, Keisuke Tateno, and Marco Hutter

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.

Music Used:

Background Music Upbeat

DELOSound

https://pixabay.com/music/soft-house-background-music-upbeat-405218/