REVIEW 8 cited by
OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
read the original abstract
Recently, significant advancements have been made in the reconstruction and generation of 3D assets, including static cases and those with physical interactions. To recover the physical properties of 3D assets, existing methods typically assume that all materials belong to a specific predefined category (e.g., elasticity). However, such assumptions ignore the complex composition of multiple heterogeneous objects in real scenarios and tend to render less physically plausible animation given a wider range of objects. We propose OmniPhysGS for synthesizing a physics-based 3D dynamic scene composed of more general objects. A key design of OmniPhysGS is treating each 3D asset as a collection of constitutive 3D Gaussians. For each Gaussian, its physical material is represented by an ensemble of 12 physical domain-expert sub-models (rubber, metal, honey, water, etc.), which greatly enhances the flexibility of the proposed model. In the implementation, we define a scene by user-specified prompts and supervise the estimation of material weighting factors via a pretrained video diffusion model. Comprehensive experiments demonstrate that OmniPhysGS achieves more general and realistic physical dynamics across a broader spectrum of materials, including elastic, viscoelastic, plastic, and fluid substances, as well as interactions between different materials. Our method surpasses existing methods by approximately 3% to 16% in metrics of visual quality and text alignment.
Forward citations
Cited by 8 Pith papers
-
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
ReconPhys is the first feedforward neural network that jointly reconstructs 3D geometry and appearance via Gaussian Splatting while estimating physical attributes from a single monocular video using self-supervised training.
-
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
-
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
MoSA learns residual stress operators on an isotropic backbone using a physics-informed cascaded network and motion constraints to capture mild anisotropy and heterogeneity for improved real-to-sim dynamics.
-
NeuROK: Generative 4D Neural Object Kinematics
NeuROK learns a data-driven latent kinematic parameterization on a large 4D dataset to generate realistic object deformations by simulating dynamics only in low-dimensional latent space via Lagrangian mechanics.
-
PhysMorph-GS: Render-Guided Volumetric Morphing with Differentiable Physics
PhysMorph-GS injects visual supervision via deformation gradients in differentiable physics simulation and uses phased Chamfer-guided plasticity to reduce silhouette error by up to 49.9% compared to physics-only baselines.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
CP4D: Compositional Physics-aware 4D Scene Generation
CP4D generates physically consistent 4D scenes via compositional integration of pre-trained 3D models, hybrid simulator-diffusion motion synthesis, and automated scene composition.
-
Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
PILA aligns frozen flow-matching video models to a physics attribute bank via MoE experts and operational residuals, reporting SOTA physical plausibility on VBench-2.0, VideoPhy-2 and PhyGenBench while preserving visu...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.