AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting

Haoran Zhou, Gim Hee Lee

CVPR 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 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
use cluster-based motion bases instead of global shared bases (ablation)MotionScale · DyCheckPSNR: 16.70 -> 17.98Improved
add adaptive cluster splitting and culling (ablation)MotionScale · DyCheckPSNR: 17.21 -> 17.98Improved
add camera pose refinement (ablation)MotionScale · DyCheckPSNR: 17.45 -> 17.98Improved
add shadow Gaussians (ablation)MotionScale · DyCheckPSNR: 16.26 -> 17.98Improved
add three-stage foreground propagation (ablation)MotionScale · DyCheckPSNR: 16.97 -> 17.98Improved
add foreground propagation (ablation)MotionScale · DyCheckAJ: 34.4 -> 37.7Improved
MotionScale vs Shape of Motion on trackingShape of Motion · DyCheck 3D trackingEPE: 0.082 -> 0.070Improved
MotionScale vs 4D-Fly4D-Fly · DyCheck NVSLPIPS: 0.37 -> 0.40Hurt

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