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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Cauchy momentum residual with time-evolving material field to static-dynamic decoupled hash model (ablation) | PIDG · PIDG dataset (average) | PSNR: 30.46 -> 30.78 | Improved |
| add Lagrangian particle flow matching loss (ablation) | PIDG · PIDG dataset (average) | PSNR: 30.78 -> 30.96 | Improved |
| add Lagrangian particle flow matching loss (ablation) | PIDG · PIDG dataset Dry Ice (fluid smoke) | SSIM: 0.897 -> 0.926 | Improved |
| add Lagrangian particle flow matching loss (ablation) | PIDG · HyperNeRF (average) | PSNR: 27.6 -> 27.8 | Improved |
| add Cauchy momentum residual material field (ablation) | PIDG · HyperNeRF (average) | PSNR: 27.5 -> 27.6 | Improved |
| add Cauchy momentum residual as plug-in regularizer (ablation) | Grid4D · D-NeRF (average) | PSNR: 42.00 -> 42.10 | Improved |
| add Cauchy momentum residual as plug-in regularizer (ablation) | SC-GS · D-NeRF (average) | PSNR: 41.65 -> 41.85 | Improved |
| add Cauchy momentum residual as plug-in regularizer (ablation) | GaussianPredict · D-NeRF (average) | PSNR: 40.58 -> 40.93 | Improved |
| add Cauchy momentum residual as plug-in regularizer (ablation) | GaussianPredict GCN · D-NeRF future prediction | PSNR: 25.22 -> 26.04 | Improved |
| add Cauchy momentum residual as plug-in regularizer (ablation) | GaussianPredict MLP · D-NeRF future prediction | PSNR: 24.64 -> 24.96 | Improved |
| add material field with Cauchy residual on top of decoupled hash model (ablation) | PIDG · PIDG dataset Dry Ice (fluid smoke) | PSNR: 25.34 -> 25.55 | No clear effect |
| add flow matching loss (ablation) | PIDG · PIDG dataset Rubber Duck (soft body) | LPIPS: 0.031 -> 0.037 | Hurt |
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.
- Grid4D — Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting (NeurIPS 2024) · better on 5 of 5 shared results
- MotionGS — MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024) · better on 1 of 1 shared result
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
- H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering (CVPR 2025 · similarity 0.90)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.90)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Gaussian Splatting Lucas-Kanade (ICLR 2025 · similarity 0.90)
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.
