AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Drop-In Perceptual Optimization for 3D Gaussian Splatting

Ezgi Ozyilkan, Zhiqi Chen, Oren Rippel, Jona Ballé, Kedar Tatwawadi

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 2 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
replace the original L1+SSIM loss with WD-R3DGS · Deep Blending (Indoors)LPIPS: 0.243 -> 0.193Improved
add a lightly weighted original pixel loss to WD (WD-R) (ablation)WD · Mip-NeRF 360 (Outdoors)LPIPS: 0.228 -> 0.206Improved
add original-loss regularizer to WD to suppress web-like artifacts (ablation)WD · Bicycle scenevisual artifactsImproved
replace the loss with WD-R in Mip-SplattingMip-Splatting · Mip-NeRF 360 (Outdoors)FID: 62.54 -> 45.87Improved
replace the loss with WD-R in Scaffold-GSScaffold-GS · Mip-NeRF 360 (Outdoors)FID: 133.33 -> 67.74Improved
replace the loss with WD-R in Scaffold-GSScaffold-GS · Mip-NeRF 360 (Indoors)CMMD: 0.391 -> 0.426Hurt
use composite loss instead of original loss3DGS · BungeeNeRF (Outdoors)LPIPS: 0.098 -> 0.197Hurt
increase LPIPS weight in composite loss from 0.1 to 0.8 (ablation)composite loss · Deep Blending (Indoors)LPIPS: 0.235 -> 0.566Hurt
decrease WD pooling sigma from 4 to 1 (ablation)WD · Mip-NeRF 360 (Indoors)LPIPS: 0.152 -> 0.134Mixed
use saliency-guided adaptive sigma instead of constant sigma=4 (ablation)WD · Mip-NeRF 360 (Indoors)LPIPS: 0.152 -> 0.155No clear effect
replace the loss with WD (no regularizer) in Mip-SplattingMip-Splatting · BungeeNeRFLPIPS: 0.113 -> 0.156Hurt
replace original loss with WD3DGS · Tanks & TemplesPSNR: 23.63 -> 22.53Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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