AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Edge Consistency for 4D Gaussian Splatting in Dynamic Scene Rendering

Boya Shi, Thomas N Guan, Yi Xiaodong

AAAI 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D 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 convex hull primitives (ablation)Gaussian baseline · D-NeRFPSNR: 31.98 -> 35.68Improved
add edge consistency regularization (ablation)Gaussian baseline · D-NeRFPSNR: 31.98 -> 34.90Improved
extend edge regularization to unit time intervals (ablation)Edge-regularized model · D-NeRFPSNR: 34.90 -> 36.24Improved
train in two stages instead of jointly (ablation)Edge4DGS · D-NeRFPSNR: 38.80 -> 40.00Improved
train in two stages instead of alternating (ablation)Edge4DGS · D-NeRFPSNR: 39.50 -> 40.00Improved
train in two stages instead of progressive resolution (ablation)Edge4DGS · D-NeRFPSNR: 37.80 -> 40.00Improved
use Edge4DGS instead of Deformable 4DGSEdge4DGS · Plenoptic Video DatasetPSNR: 28.42 -> 35.33Improved
use Edge4DGS instead of K-PlanesEdge4DGS · Plenoptic Video DatasetLPIPS: 0.07 -> 0.07No clear effect
use Edge4DGS instead of Deformable3DGSEdge4DGS · D-NeRFPSNR: 39.31 -> 40.00Mixed

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