AI Paper Atlas

Research map / 3D vision / Gaussian splatting

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

Chonghao Zhong, Linfeng Shi, Chen Hua, Tiecheng Sun, Hao Zhao, Binhang Yuan, Chaojian Li

ICML 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add trajectory-adaptive differential streaming (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)PCIe traffic (GB/iter): 0.85 -> 0.10Improved
add trajectory-adaptive differential streaming (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)iteration time (ms): 145.3 -> 90.7Improved
add asynchronous overlap of I/O and compute (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)iteration time (ms): 210.5 -> 90.7Improved
add Morton-ordered block layout (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)CPU cache hit rate (%): 42.1 -> 95.2Improved
add Morton-ordered block layout (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)PCIe traffic (GB/iter): 0.45 -> 0.10Improved
add differential streaming or overlap (ablation)TideGS · MatrixCity BigCity/Aerial (~102M Gaussians)PSNR: 24.79 / 24.86 vs 24.83No clear effect
use trajectory (TSP-ordered) camera sequence instead of shuffle (ablation)TideGS · Mip-NeRF 360 in-memorythroughput (img/s): 3.24 -> 3.50Improved
scale Gaussians from ~102M to ~1.1B with out-of-core trainingTideGS · MatrixCityPSNR: 24.8 -> 26.1Improved
use block virtualization instead of native in-memory 3DGSTideGS · Mip-NeRF 360PSNR: 29.0252 -> 28.9157No clear effect
replace CLM offloading with TideGS SSD-CPU-GPU hierarchyCLM vs TideGS · MatrixCity ~1.1BfeasibilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy