AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting

Andrew Bond, Jui-Hsien Wang, Long Mai, Erkut Erdem, Aykut Erdem

ICCV 2025 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 14 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 spatial hierarchical learning to temporal-only (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 42.8404 -> 43.2110Improved
add temporal hierarchical learning to spatial-only (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 42.2068 -> 43.2110Improved
add hierarchical learning (spatial and temporal) (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 40.2016 -> 43.2110Improved
add spatial hierarchical learning (ablation)GaussianVideo · DL3DV (1K, 540p)training time: ~ 40 mins -> ~ 35 minsImproved
add Neural ODE camera model instead of static learned camera (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 33.9304 -> 43.2110Improved
add camera model (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 21.1821 -> 43.2110Improved
use B-spline motion instead of polynomial (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 20.1871 -> 43.2110Improved
learn all SH coefficients at once instead of incremental (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 31.0736 -> 43.2110Improved
allow Gaussian scale to vary over time (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 34.1585 -> 43.2110Improved
add warping of unused Gaussians (ablation)GaussianVideo · DL3DV (1K, 540p)PSNR: 34.0106 -> 43.2110Improved
add hierarchical learning (spatial and temporal) (ablation)GaussianVideo · DL3DV (1K, 540p)LPIPS: 0.0177 -> 0.0125Improved
increase Gaussian count beyond 400K (ablation)GaussianVideo · DL3DV and DAVISPSNR/SSIM/LPIPSNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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