AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

Otto Seiskari, Jerry Ylilammi, Valtteri Kaatrasalo, Pekka Rantalankila, Matias Turkulainen, Juho Kannala, Esa Rahtu, Arno Solin

ECCV 2024 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 29 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 blur compensation via screen-space pixel velocitiesSplatfacto 3DGS · Synthetic Cozyroom motion blurPSNR: 26.63 -> 32.20Improved
add rolling shutter compensationSplatfacto 3DGS · Synthetic Cozyroom rolling shutterPSNR: 19.21 -> 35.84Improved
add pose optimization with velocity compensationSplatfacto 3DGS · Synthetic Cozyroom pose noisePSNR: 16.76 -> 36.30Improved
apply method to the Pool scene with motion blurSplatfacto 3DGS · Synthetic Pool motion blurPSNR: 35.50 -> 35.27No clear effect
use 3DGS with blur and RS model instead of NeRF-based BAD-NeRFOurs · Deblur-NeRF BAD-NeRF variantPSNR: Cozyroom 30.97 -> 31.80; Factory 31.65 -> 30.54Mixed
add motion blur compensation (ablation)Ours on smartphone data · Smartphone data averagePSNR: 27.99 -> 28.59Improved
add rolling shutter compensation (ablation)Ours on smartphone data · Smartphone data averagePSNR: 27.62 -> 28.59Improved
add pose optimization (ablation)Ours on smartphone data · Smartphone data averagePSNR: 27.44 -> 28.59Improved
add velocity optimization (ablation)Ours on smartphone data · Smartphone data averagePSNR: 27.65 -> 28.59Improved
add VIO-based velocity initialization (ablation)Ours on smartphone data · Smartphone data averagePSNR: 28.19 -> 28.59Improved
replace built-in rolling shutter modeling by CVR de-rolling preprocessing (ablation)Ours on smartphone data · Smartphone data averagePSNR: 28.59 -> 26.49Hurt
enable full blur and RS compensationOurs · Smartphone data training timetraining time (min), average: 19 -> 91Hurt

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