AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LiteGS: a high-performance framework to train 3dgs in subminutes via system and algorithm codesign

Kaimin Liao, Hua Wang, Zhi Chen, Luchao Wang, Yaohua Tang

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 11 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 Cluster-Cull-Compact (ablation)LiteGS-quality · Mip-NeRF 360Training time (s): 701 -> 515Improved
add Cluster-Cull-Compact (ablation)LiteGS-quality · Mip-NeRF 360PSNR (dB): 28.28 -> 28.25No clear effect
add Cluster-Cull-Compact (ablation)LiteGS-quality · Deep BlendingTraining time (s): 533 -> 330Improved
warp-based rasterizer instead of atomic raster (ablation)LiteGS · garden scene backward passBackward time (ms): 51.84 -> 6.93Improved
warp-based rasterizer instead of per-splat raster (ablation)LiteGS · garden scene backward passBackward time (ms): 27.31 -> 6.93Improved
add opacity decay instead of hard reset (ablation)LiteGS · Mip-NeRF 360PSNR (dB): 27.68 -> 28.12Improved
add opacity-gradient variance densification metric (ablation)LiteGS · Mip-NeRF 360PSNR (dB): 27.40 -> 28.12Improved
add both opacity decay and variance metric (ablation)LiteGS · Mip-NeRF 360PSNR (dB): 27.13 -> 28.12Improved
add opacity decay and variance metric (ablation)LiteGS · Deep BlendingPSNR (dB): 29.76 -> 30.37Improved
LiteGS-quality vs 3DGS-MCMCLiteGS · Mip-NeRF 360PSNR (dB): 28.08 -> 28.25Improved
LiteGS-turbo vs Mini-Splatting v2LiteGS · Mip-NeRF 360Training time (s): 214 -> 145Improved
LiteGS-turbo vs Mini-Splatting v2 on perceptual qualityLiteGS · Mip-NeRF 360LPIPS: 0.215 -> 0.236Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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