AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting

Junseo Koo, Jinseo Jeong, Gunhee Kim

AAAI 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 1 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 scalar alpha blending with Gaussian BlendingAnalytic-Splatting / Mip-Splatting · Multi-scale Blender (train x1)PSNR avg: 31.59 -> 35.58Improved
replace scalar alpha blending with Gaussian BlendingMip-Splatting · Multi-scale Blender (train x1/8)PSNR avg: 29.64 -> 31.04Improved
replace scalar alpha blending with Gaussian BlendingMip-Splatting · Multi-scale Blender (multi-scale training)PSNR avg: 34.72 -> 36.19Improved
replace scalar alpha blending with Gaussian BlendingMip-Splatting · Mip-NeRF 360 (train x1)PSNR avg: 28.47 -> 29.17Improved
replace scalar alpha blending with Gaussian BlendingMip-Splatting · Mip-NeRF 360 (multi-scale training)PSNR avg: 29.25 -> 29.53Improved
swap in Gaussian Blending kernel at test time only (ablation)Mip-Splatting · Multi-scale Blender (train x1)PSNR avg: 31.73 -> 35.54Improved
swap in Gaussian Blending kernel at test time only (ablation)Mip-Splatting · Multi-scale Blender (train x1/8)PSNR avg: 29.64 -> 29.12Hurt
swap in Gaussian Blending kernel at test time only (ablation)Analytic-Splatting · Multi-scale Blender (train x1/8)PSNR avg: 29.53 -> 28.78Hurt
use Gaussian Blending kernel in training and inference (ablation)Scaffold-GS · Multi-scale Blender (train x1)PSNR avg: 24.92 -> 32.47Improved
reimplement spatial alpha blending in native kernel (ablation)2DGS · Multi-scale Blender (train x1)PSNR avg: 23.79 -> 33.79Improved
use Gaussian Blending kernel in training and inference (ablation)Scaffold-GS · Multi-scale Blender (train x1/8)PSNR avg: 22.37 -> 30.41Improved
use Gaussian Blending kernel at x1 resolutionGaussian Blending vs Mip-Splatting · Multi-scale Blender (train x1)PSNR x1: 33.54 -> 33.92No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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