AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering

Ankit Dhiman, Kunal A Kathare, Pranav Vignesh, LOKESH BOREGOWDA, Venkatesh Babu Radhakrishnan

ECCV 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 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-aware smoothing filter to SpeeDe3DGSSpeeDe3DGS · D-NeRF 4x testPSNR: 27.83 -> 32.28Improved
add motion-aware smoothing filter to SpeeDe3DGSSpeeDe3DGS · D-NeRF 4x testtraining time (min): 4.45 -> 6.48Hurt
add motion-aware filter when rendering at 1/4x resolutionSpeeDe3DGS · D-NeRF zoom-out (1/4x)PSNR: 28.10 -> 35.87Improved
add motion-aware filter at training resolutionSpeeDe3DGS · D-NeRF zoom-out (1x)PSNR: 35.01 -> 35.02No clear effect
use motion-aware filter instead of static 3D Mip-Splatting filterSARO-GS + 3D Filter · Plenoptic VideoPSNR: 24.92 -> 6.4 dB improvementImproved
add motion-aware filter to SARO-GSSARO-GS · Plenoptic Video (train 1x, multi-scale test)PSNR avg: 29.85 -> 31.01Improved
add motion-aware filter to SARO-GS at same-scale testingSARO-GS · Plenoptic Video (single-scale)SSIM: 0.004 SSIM decreaseHurt
temporal grid size T=100 instead of 25 (ablation)Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale)PSNR 4x: 30.58 -> 31.72Improved
temporal grid size T=100 instead of 150 (ablation)Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale)PSNR 4x: 31.11 -> 31.72Improved
update filter every 100 iterations instead of 300 (ablation)Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale)PSNR 4x: 29.34 -> 31.72Improved
update filter every 100 iterations instead of 200 (ablation)Motion-aware filter · D-NeRF (SARO-GS, train 1x, multi-scale)PSNR 4x: 30.64 -> 31.72Improved
increase kernel bandwidth h_x from 0.1 to 0.3 (ablation)Motion-aware filter + SpeeDe3DGS · D-NeRF 4x testPSNR: 32.13 -> 32.28No 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