AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Gradient-Direction-Aware Density Control for 3D Gaussian Splatting

Zheng Zhou, Yu-Jie Xiong, Jia-Chen Zhang, Chun-Ming Xia, Xihe Qiu, Hongjian Zhan

ICLR 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
nonlinear (power) weighting instead of linear weighting (ablation)GDAGS · Mip-NeRF360 (9 scenes)PSNR / SSIM / LPIPS: SSIM 0.814 -> 0.839; PSNR 27.55 -> 28.02; LPIPS 0.248 -> 0.145Improved
apply GCR weighting during splitting only (ablation)GDAGS · Mip-NeRF360 (9 scenes)memory / SSIM / LPIPS: memory 734MB -> 441MB; SSIM 0.815 -> 0.819Mixed
apply GCR weighting during cloning only (ablation)GDAGS · Mip-NeRF360 (9 scenes)PSNR / memory: PSNR 27.21 -> 27.46; memory 734MB -> 615MBMixed
apply GCR weighting in both splitting and cloning (ablation)GDAGS · Mip-NeRF360 (9 scenes)SSIM / PSNR / LPIPS: SSIM 0.839, PSNR 28.02, LPIPS 0.145 vs best single-sided 0.819, 27.52, 0.217Improved
increase p from 10 to 30 (ablation)GDAGS · Mip-NeRF360, Tanks&Temples, Deep Blendingmemory and rendering qualityMixed
increase beta from 15 to 35 (ablation)GDAGS · three datasetsperformance and storageNo clear effect
use exponential instead of power function in weighting (ablation)GDAGS · three datasetstraining time: 1140s -> 1200s (+5.2%) on Mip-NeRF360Hurt
exponential instead of power function (ablation)GDAGS · Mip-NeRF360 (9 scenes)PSNR: 28.02 -> 27.96Hurt
add GDAGS to MCMC-3DGSMCMC-3DGS · Mip-NeRF360 (9 scenes)LPIPS: 0.190 -> 0.150Improved
add GDAGS to MCMC-3DGSMCMC-3DGS · Mip-NeRF360 (9 scenes)PSNR: 29.89 -> 29.80Hurt
add GDAGS to Compact-3DGSCompact-3DGS · Mip-NeRF360 (9 scenes)LPIPS: 0.247 -> 0.227Improved
add opacity-weighted Gaussian dropout 5% (ablation)GDAGS · Deep BlendingPSNR: 29.70 -> 30.03Improved

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