AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Racing in Volume with Flow Ensembles

Saswat Subhajyoti Mallick, Riu Cherdchusakulchai, Marc Ruiz, Albert Mosella-Montoro, Jose Ribeiro-Gomes, Francisco Vicente Carrasco, Fernando de la Torre

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 Kalman temporal prior (ablation)FastFlowGS · CMU-Panoptic FootballVMAF: 46.82 -> 49.37Improved
add Kalman temporal prior (ablation)FastFlowGS · Monaco4D FairmontVMAF: 41.17 -> 43.93Improved
add Kalman temporal prior (ablation)FastFlowGS · Monaco4D Fairmontiterations to threshold: 760 -> 700Improved
add cross-level disagreement filter (ablation)FastFlowGS · CMU-Panoptic Footballiterations to 24+ PSNR: 300 -> 260Improved
add cross-level disagreement filter (ablation)FastFlowGS · CMU-Panoptic FootballVMAF: 46.49 -> 46.82Improved
fuse sparse and dense correspondences (ablation)FastFlowGS · CMU-Panoptic FootballVMAF: 46.14 / 45.32 -> 46.49Improved
dense instead of sparse correspondences (ablation)FastFlowGS · CMU-Panoptic FootballM-PSNR: 25.31 vs 25.29No clear effect
dense instead of sparse correspondences (ablation)FastFlowGS · Monaco4D FairmontVMAF: 39.33 -> 40.76Improved
fuse multi-resolution correspondences with Kalman prior vs 3DGS-BaseFastFlowGS · Monaco4D FairmontM-PSNR: 16.4 -> 18.88Improved
use FastFlowGS under 5x frame skipping vs QUEENFastFlowGS · CMU-Panoptic (5x frame skip)VMAF: 51.16 -> 50.66Hurt
hash-grid streaming baselines under 5x frame skipping3DGStream · CMU-Panoptic (5x frame skip)PSNR: 27.189 -> 21.68Hurt
streaming baselines on Monaco4D full-quality protocolexisting streaming methods · Monaco4DreconstructionHurt

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