REVIEW 27 cited by
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
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
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
read the original abstract
In recent years, there has been rapid development in 3D generation models, opening up new possibilities for applications such as simulating the dynamic movements of 3D objects and customizing their behaviors. However, current 3D generative models tend to focus only on surface features such as color and shape, neglecting the inherent physical properties that govern the behavior of objects in the real world. To accurately simulate physics-aligned dynamics, it is essential to predict the physical properties of materials and incorporate them into the behavior prediction process. Nonetheless, predicting the diverse materials of real-world objects is still challenging due to the complex nature of their physical attributes. In this paper, we propose \textbf{Physics3D}, a novel method for learning various physical properties of 3D objects through a video diffusion model. Our approach involves designing a highly generalizable physical simulation system based on a viscoelastic material model, which enables us to simulate a wide range of materials with high-fidelity capabilities. Moreover, we distill the physical priors from a video diffusion model that contains more understanding of realistic object materials. Extensive experiments demonstrate the effectiveness of our method with both elastic and plastic materials. Physics3D shows great potential for bridging the gap between the physical world and virtual neural space, providing a better integration and application of realistic physical principles in virtual environments. Project page: https://liuff19.github.io/Physics3D.
Forward citations
Cited by 27 Pith papers
-
PhysInOne: Visual Physics Learning and Reasoning in One Suite
PhysInOne is a new dataset of 2 million videos across 153,810 dynamic 3D scenes covering 71 physical phenomena, shown to improve AI performance on physics-aware video generation, prediction, property estimation, and m...
-
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
A Representation Abstraction Framework converts 3DGS, meshes, and fluids into unified particles for scene-level heterogeneous multi-solver physics simulation.
-
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.
-
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
FieryGS integrates LLM-based material reasoning, volumetric combustion simulation, and a unified renderer with 3D Gaussian Splatting to generate physically plausible and user-controllable fire in in-the-wild scenes.
-
ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation
ProJo4D uses progressive joint optimization to solve sparse-view inverse physics estimation, outperforming prior methods with up to 10x better geometric accuracy in 4D state prediction and material estimation.
-
DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization
DeGS restructures 3DGS rendering into span parsing, task reorganization, and dense blending stages, achieving 1.8x-7.2x speedup and >80% scaling utilization over prior 3DGS accelerators.
-
DR-GS: Physically-Based Deformable and Relightable 2D Gaussians
DR-GS is a unified 2D Gaussian framework that integrates physically-based inverse rendering, relighting, and deformation by explicitly disentangling geometry, illumination, and material representations.
-
Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection
A self-supervised framework learns implicit 3D physics by lifting V-JEPA features into voxels and performing volumetric feature advection conditioned on actions.
-
Streaming Video Generation with Streaming Force Control
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-o...
-
MatPhys: Learning Material-Aware Physics Parameters for Deformable Object Simulation from Videos
MatPhys is a feed-forward framework that predicts consistent part-level spring-mass parameters for deformable object simulation from monocular videos using semantic decomposition and a material embedding codebook.
-
EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting
EndoGSim integrates MLLM-guided material initialization with 4D Gaussian Splatting and differentiable Material Point Method to achieve physics-aware 4D reconstruction and simulation of endoscopic scenes.
-
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
VideoGPA distills geometry priors via self-supervised DPO to enhance 3D consistency, temporal stability, and motion coherence in video diffusion models.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics
PhysCoRe uses a differentiable MPM simulator with neural material inference and residual velocity correction, and reports more accurate future prediction on real deformable-object manipulation than optimization baselines.
-
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.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV introduces a hierarchical Monte Carlo estimator with amortized reuse, importance sampling, and stratification that yields 2-3x effective compute gains on diffusion-teacher pipelines while cutting gradient varianc...
-
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
FieryGS couples MLLM-based material reasoning with simplified combustion simulation and unified fire/smoke/3DGS rendering to synthesize controllable, scene-consistent fire in reconstructed real-world scenes.
-
InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model
InSpatio-WorldFM is a frame-independent generative model that uses explicit 3D anchors and spatial memory to deliver real-time multi-view consistent spatial intelligence via a three-stage training pipeline from pretra...
-
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
Using VGGT's reconstruction error as a self-supervised reward, DPO post-training with ~2,500 preference pairs improves 3D consistency of CogVideoX-based video generation while preserving perceptual quality.
-
Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction
A pipeline combining SAM2 segmentation, 3D Gaussian Splatting, and joint Score Distillation Sampling with 2D/3D diffusion priors reconstructs decoupled multi-object geometries from occluded sparse views for MPM simulation.
-
Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction
A new pipeline for occlusion-robust multi-object 3D reconstruction from sparse views supports physics-based robotic interaction.
-
CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction
The paper's stated CA-World counterfactual claim is absent from the body, which instead describes the SAM3D-Phys pipeline for multi-object interactive reconstruction and simulation.
-
CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction
SAM3D-Phys recovers complete simulatable object geometries from incomplete real-world scene reconstructions by combining SAM3D generative priors with physics-constrained spatial optimization and mask-guided appearance...
-
A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
A survey that categorizes and summarizes methods applying 3D Gaussian Splatting to segmentation, editing, generation, and related tasks, including datasets and evaluation protocols.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
-
A Survey on 3D Gaussian Splatting
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.