AI Paper Atlas

Research map / 3D vision / Gaussian splatting

PhysConvex: Physics-Informed Dynamic Convex Fields for Reconstruction and Simulation

Dan Wang, Xinrui Cui, Serge Belongie, Ravi Ramamoorthi

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
Use boundary-driven convex primitives with reduced-order simulation instead of Gaussian-based Vid2SimVid2Sim · GSO dynamic reconstructionPSNR: 28.57 -> 30.00Improved
Same change on system identificationVid2Sim · GSO system identificationMAE log(E): 0.51 -> 0.37Improved
Same change on future state predictionVid2Sim · GSO future state predictionPSNR: 25.07 -> 25.71Improved
Same change on future state FoVVDPVid2Sim · GSO future state predictionFoVVDP: 7.770 -> 7.683No clear effect
Increase convex points K from 3 to 6 (ablation)PhysConvex · GSO dynamic reconstructionPSNR: 24.90 -> 30.00Improved
Increase K from 6 to 8 (ablation)PhysConvex · GSO dynamic reconstructionPSNR: 30.00 -> 30.19No clear effect
Increase K from 6 to 8 (ablation)PhysConvex · GSO future state predictionPSNR: 25.71 -> 25.38No clear effect
Vary reduced DOFs M from 10 to 8 or 12 (ablation)PhysConvex (K=6) · GSO dynamic reconstructionPSNR: 30.00 vs 29.96 / 29.88No clear effect
Use convex primitives instead of Gaussian/NeRF baselinesPAC-NeRF · GSOAvg training time: 51 min -> 6 minImproved

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