TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization

• URL: http://arxiv.org/abs/2605.20150v2
• Date: Tue, 26 May 2026 20:15:21 GMT
• Title: TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
• Abstract summary: Training 3DGS at billion-primitive scale is fundamentally memory-bound.<n>TideGS is an out-of-core training framework that manages parameters across an SSD- CPU- GPU hierarchy.<n>TideGS enables training with over one billion Gaussians on a single 24 GB GPU.
• Score: 19.191940595279206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector, and the aggregate parameter table quickly exceeds GPU capacity, limiting prior systems to tens of millions of Gaussians on commodity single-GPU hardware. We observe that 3DGS training is inherently sparse and trajectory-conditioned: each iteration activates only the Gaussians visible from the current camera batch, so GPU memory can serve as a working-set cache rather than a persistent parameter store. Building on this insight, we introduce TideGS, an out-of-core training framework that manages parameters across an SSD-CPU-GPU hierarchy via three synergistic techniques: block-virtualized geometry for SSD-aligned spatial locality, a hierarchical asynchronous pipeline to overlap I/O with computation, and trajectory-adaptive differential streaming that transfers only incremental working-set deltas between iterations. Experiments show that TideGS enables training with over one billion Gaussians on a single 24 GB GPU while achieving the best reconstruction quality among evaluated single-GPU baselines on large-scale scenes, scaling beyond prior out-of-core baselines (e.g., approximately 100M Gaussians) and standard in-memory training (e.g., approximately 11M Gaussians).

Related papers

• Local-GS: Accelerating 3D Gaussian Splatting via Tile-Local Warp Coherence [31.001161060131622]
  3D Gaussian Splatting (3DGS) has significantly advanced real-time novel view computation by representing scenes as dense collections of anisotropic 3D Gaussian primitives.<n>We present Local-GS, a warp-coherent rendering paradigm that organizes Gaussian primitives with respect to SIMT (Single Instruction, Multiple Threads) execution boundaries rather than scene geometry.<n>As a plug-and-play optimization, it provides additional performance gains to all tested baselines, culminating in a $7.76times$ speedup on Deep Blending scenes.
  arXiv  Detail & Related papers  (2026-06-15T11:08:10Z)
• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading [9.776813771006358]
  3D Gaussian Splatting has revolutionized graphics rendering by delivering high visual quality and fast rendering speeds.<n>Training large-scale scenes at high quality remains challenging due to substantial memory demands.<n>We propose GS-Scale, a fast and memory-efficient training system for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-09-19T06:13:28Z)
• Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS [13.03299802566674]
  3DGS has emerged as a powerful technique for radiance field rendering, but it typically requires millions of redundant Gaussian primitives.<n>We propose a novel optimal transport perspective that casts 3DGS compaction as global Gaussian mixture reduction.<n>Our method is applicable to any stage of vanilla or accelerated 3DGS pipelines, providing an efficient and agnostic pathway to lightweight neural rendering.
  arXiv  Detail & Related papers  (2025-06-11T09:04:44Z)
• FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting [57.97160965244424]
  3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis.<n>Previous approaches have focused on pruning less important Gaussians, effectively compressing 3DGS.<n>We present an elastic inference method for 3DGS, achieving substantial rendering performance without additional fine-tuning.
  arXiv  Detail & Related papers  (2025-06-04T17:17:57Z)
• 3DGS$^2$: Near Second-order Converging 3D Gaussian Splatting [26.94968605302451]
  3D Gaussian Splatting (3DGS) has emerged as a mainstream solution for novel view synthesis and 3D reconstruction.<n>This paper introduces a (near) second-order convergent training algorithm for 3DGS, leveraging its unique properties.
  arXiv  Detail & Related papers  (2025-01-22T22:28:11Z)
• MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes [49.36091070642661]
  This paper introduces a memory-efficient framework for 4DGS.<n>It achieves a storage reduction by approximately 190$times$ and 125$times$ on the Technicolor and Neural 3D Video datasets.<n>It maintains comparable rendering speeds and scene representation quality, setting a new standard in the field.
  arXiv  Detail & Related papers  (2024-10-17T14:47:08Z)
• On Scaling Up 3D Gaussian Splatting Training [31.161086345038424]
  3DGS is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed.<n>Currently, 3DGS training occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks.<n>We introduce Grendel, a distributed system designed to partition 3DGS parameters and parallelize across multiple GPU.
  arXiv  Detail & Related papers  (2024-06-26T17:59:28Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.