AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field

Haoqin Hong, Ding Fan, Fubin Dou, Zhi-Li Zhou, Haoran Sun, Congcong Zhu, Jingrun Chen

AAAI 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 3 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 Cauchy momentum residual with time-evolving material field to static-dynamic decoupled hash model (ablation)PIDG · PIDG dataset (average)PSNR: 30.46 -> 30.78Improved
add Lagrangian particle flow matching loss (ablation)PIDG · PIDG dataset (average)PSNR: 30.78 -> 30.96Improved
add Lagrangian particle flow matching loss (ablation)PIDG · PIDG dataset Dry Ice (fluid smoke)SSIM: 0.897 -> 0.926Improved
add Lagrangian particle flow matching loss (ablation)PIDG · HyperNeRF (average)PSNR: 27.6 -> 27.8Improved
add Cauchy momentum residual material field (ablation)PIDG · HyperNeRF (average)PSNR: 27.5 -> 27.6Improved
add Cauchy momentum residual as plug-in regularizer (ablation)Grid4D · D-NeRF (average)PSNR: 42.00 -> 42.10Improved
add Cauchy momentum residual as plug-in regularizer (ablation)SC-GS · D-NeRF (average)PSNR: 41.65 -> 41.85Improved
add Cauchy momentum residual as plug-in regularizer (ablation)GaussianPredict · D-NeRF (average)PSNR: 40.58 -> 40.93Improved
add Cauchy momentum residual as plug-in regularizer (ablation)GaussianPredict GCN · D-NeRF future predictionPSNR: 25.22 -> 26.04Improved
add Cauchy momentum residual as plug-in regularizer (ablation)GaussianPredict MLP · D-NeRF future predictionPSNR: 24.64 -> 24.96Improved
add material field with Cauchy residual on top of decoupled hash model (ablation)PIDG · PIDG dataset Dry Ice (fluid smoke)PSNR: 25.34 -> 25.55No clear effect
add flow matching loss (ablation)PIDG · PIDG dataset Rubber Duck (soft body)LPIPS: 0.031 -> 0.037Hurt

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