Saved in:
Bibliographic Details
Main Authors: Feldmann, Casimir, Wilder-Smith, Maximum, Patil, Vaishakh, Oechsle, Michael, Niemeyer, Michael, Tateno, Keisuke, Hutter, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.23030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908679975993344
author Feldmann, Casimir
Wilder-Smith, Maximum
Patil, Vaishakh
Oechsle, Michael
Niemeyer, Michael
Tateno, Keisuke
Hutter, Marco
author_facet Feldmann, Casimir
Wilder-Smith, Maximum
Patil, Vaishakh
Oechsle, Michael
Niemeyer, Michael
Tateno, Keisuke
Hutter, Marco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_23030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management
Feldmann, Casimir
Wilder-Smith, Maximum
Patil, Vaishakh
Oechsle, Michael
Niemeyer, Michael
Tateno, Keisuke
Hutter, Marco
Robotics
Computer Vision and Pattern Recognition
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.
title DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.23030