AI Paper Atlas

Research map / 3D vision / Gaussian splatting

NanoGS: Training-Free and Lightweight Gaussian Splat Simplification

Butian Xiong, Rong Liu, Tiantian Zhou, Meida Chen, Zhiwen Fan, Andrew Feng

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS

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
use KNN-graph candidate selection instead of Octree-based selection (ablation)NanoGS · Mip-NeRF 360 (rho=0.001)PSNR (dB): 14.11 -> 17.20Improved
use KNN-graph candidate selection instead of Octree-based selection (ablation)NanoGS · NeRF Synthetic (rho=0.001)PSNR (dB): 15.85 -> 19.04Improved
add opacity-based filtering before merging (ablation)NanoGS · Mip-NeRF 360 (rho=0.001)PSNR (dB): 14.67 -> 17.20Improved
add opacity-based filtering before merging (ablation)NanoGS · NeRF Synthetic (rho=0.001)PSNR (dB): 18.87 -> 19.04Improved
add opacity-based filtering before merging (ablation)NanoGS · NeRF Synthetic (rho=0.1)PSNR (dB): 24.99 -> 25.81Improved
use I-divergence geometric cost instead of MSE surrogate (ablation)NanoGS · Mip-NeRF 360 (rho=0.001)PSNR (dB): 16.98 -> 17.20Improved
use I-divergence geometric cost instead of MSE surrogate (ablation)NanoGS · NeRF Synthetic (rho=0.001)PSNR (dB): 18.80 -> 19.04Improved
NanoGS vs best baseline (no fine-tuning), averaged over datasetsNanoGS · 4 benchmarks (rho=0.1)PSNR (dB): +2.40 dBImproved
NanoGS vs best baseline, rho=0.01NanoGS · 4 benchmarks (rho=0.01)PSNR (dB): +4.84 dBImproved
NanoGS vs best baseline, rho=0.001NanoGS · 4 benchmarks (rho=0.001)PSNR (dB): +5.46 dBImproved
increase Monte Carlo samples from S=1 to S=128 (ablation)NanoGS · merge cost estimationquality: S=1 vs S=128No clear effect
chain SOG compression on top of NanoGS compactionNanoGS · 60 models storagestorage: 16.83 -> 2.45 (6.35x)Improved

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