AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization

Zheng Dong, Daifei Qiu, Pinxuan Dai, Ke Xu, Jiamin Xu, Lili He, Rynson W. H. Lau, Weiwei Xu

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 error-guided sparse pixel sampling (Err-SPS) (ablation)3DGS · Mip-NeRF 360training time (s): 891 -> 85Improved
add error-guided sparse pixel sampling (Err-SPS) (ablation)3DGS · Mip-NeRF 360PSNR: 27.55 -> 26.58Hurt
add geometry-aware view sampling (Geo-VS) (ablation)3DGS + Err-SPS · Mip-NeRF 360PSNR: 26.58 -> 26.73Improved
add sparse NCC loss (ablation)3DGS + Err-SPS + Geo-VS · Mip-NeRF 360PSNR: 26.73 -> 27.14Improved
add error-driven density control (Err-DP) (ablation)3DGS + Err-SPS + Geo-VS + sparse NCC · Mip-NeRF 360PSNR: 27.14 -> 27.57Improved
use error-guided sparse pixel sampling instead of random pixel sampling (ablation)TurboGS · Mip-NeRF 360PSNR: 27.10 -> 27.57Improved
use geometry-aware view sampling instead of random view sampling (ablation)TurboGS · Mip-NeRF 360PSNR: 27.26 -> 27.57Improved
use error-driven density control instead of FastGS-style density control (ablation)TurboGS · Mip-NeRF 360training time (s): 91 -> 77Improved
add sparse NCC to l1 loss (ablation)TurboGS · Mip-NeRF 360PSNR: 27.09 -> 27.57Improved
use sparse NCC instead of sparse SSIM (ablation)TurboGS · Mip-NeRF 360LPIPS: 0.287 -> 0.256Improved
use moment-damped LM instead of sparse Adam (ablation)TurboGS · Mip-NeRF 360PSNR: 27.52 -> 27.57Improved
use adaptive view budget 10 to 3 instead of fixed K=1 (ablation)TurboGS · Mip-NeRF 360PSNR: 26.50 -> 27.57Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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