AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting

Jianwei Hu, Tingxuan Huang, Hengyu Zhou, Ningna Wang, Xiaohu Guo, Jinshan Lai, Bin Wang

ECCV 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 motion-variance guided refinement and MotionFormer temporal attentionDeGauss · NeRF On-the-go backgroundLPIPS: 0.113 -> 0.085Improved
add MVG+MFTADeGauss · NeRF On-the-go foregroundPSNR: 22.93 -> 27.60Improved
add MVG+MFTADeGauss · RobustNeRFPSNR: 28.89 -> 29.39Improved
add MVG+MFTADeGauss · Neu3DPSNR: 31.52 -> 32.07Improved
add MVG+MFTA plug-in to 4DGS without decomposition4DGS · Neu3DPSNR: 31.12 -> 31.66Improved
add motion statistics (global trajectory signature) with position variance only (ablation)MVFusion-GS · Neu3DPSNR: 31.52 -> 31.93Improved
use full 13D signature instead of position-only variance (ablation)MVFusion-GS · Neu3DPSNR: 31.93 -> 32.07Improved
add MFTA temporal attention (ablation)MVFusion-GS · Neu3DPSNR: 31.78 -> 32.07Improved
use query-centered cross-attention instead of self-attention (ablation)MFTA · Neu3DPSNR: 32.01 -> 32.07Improved
add MVG+MFTA refinement (ablation)DeGauss · NeRF On-the-go backgroundPSNR: 23.86 -> 23.94No clear effect
add MVG (ablation)MVFusion-GS · Neu3DSSIM: w/o MVG SSIM 0.937 vs base 0.942 vs full 0.943Mixed
use 0.7/0.2/0.1 weighted motion score instead of uniform weights (ablation)MVG · Neu3DPSNR: 31.88 -> 32.07Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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