# PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation

arXiv: https://arxiv.org/abs/2411.14423 · HTML: https://mlsanity.com/paper/2411.14423/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 39 of its 50 references that are in the map.
- First posted on arXiv 21 Nov 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation](https://mlsanity.com/paper/2404.13026/) (2024)
- [Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2408.13912/) (2024)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification](https://mlsanity.com/paper/2303.05512/) (2023)
- [MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model](https://mlsanity.com/paper/2405.20222/) (2024)
- [Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion](https://mlsanity.com/paper/2406.04338/) (2024)
- [RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools](https://mlsanity.com/paper/2306.14447/) (2023)
- [DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos](https://mlsanity.com/paper/2405.02280/) (2024)
- [HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction](https://mlsanity.com/paper/2410.06245/) (2024)
- [IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis](https://mlsanity.com/paper/2210.00647/) (2022)
- [GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation](https://mlsanity.com/paper/2406.14927/) (2024)
- [Learning 3D Dynamic Scene Representations for Robot Manipulation](https://mlsanity.com/paper/2011.01968/) (2020)
- [DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion](https://mlsanity.com/paper/2410.24203/) (2024)
- [Neural Stress Fields for Reduced-order Elastoplasticity and Fracture](https://mlsanity.com/paper/2310.17790/) (2023)

## Built on by (most cited first, 30 of 36)

- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [Exploring the Evolution of Physics Cognition in Video Generation: A Survey](https://mlsanity.com/paper/2503.21765/) (2025)
- [Generative Physical AI in Vision: A Survey](https://mlsanity.com/paper/2501.10928/) (2025)
- [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://mlsanity.com/paper/2510.19022/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC](https://mlsanity.com/paper/2502.07007/) (2025)
- [PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding](https://mlsanity.com/paper/2511.20562/) (2025)
- [SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials](https://mlsanity.com/paper/2504.12684/) (2025)
- [PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM](https://mlsanity.com/paper/2505.16456/) (2025)
- [ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation](https://mlsanity.com/paper/2506.05317/) (2025)
- [VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization](https://mlsanity.com/paper/2508.13792/) (2025)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics](https://mlsanity.com/paper/2603.09668/) (2026)
- [MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos](https://mlsanity.com/paper/2605.30320/) (2026)
- [Zero-Shot 3D Visual Grounding from Vision-Language Models](https://mlsanity.com/paper/2505.22429/) (2025)
- [MotionPhysics: Learnable Motion Distillation for Text-Guided Simulation](https://mlsanity.com/paper/2601.00504/) (2026)
- [FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting](https://mlsanity.com/paper/2605.00177/) (2026)
- [DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos](https://mlsanity.com/paper/2605.09586/) (2026)
- [Physically Viable World Models: A Case for Query-Conditioned Embodied AI](https://mlsanity.com/paper/2605.30542/) (2026)
- [CP4D: Compositional Physics-aware 4D Scene Generation](https://mlsanity.com/paper/2606.09187/) (2026)
- [DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum](https://mlsanity.com/paper/2510.22213/) (2025)
- [Inferring Compositional 4D Scenes without Ever Seeing One](https://mlsanity.com/paper/2512.05272/) (2025)
- [M-PhyGs: Multi-Material Object Dynamics from Video](https://mlsanity.com/paper/2512.16885/) (2025)
- [UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing](https://mlsanity.com/paper/2603.08131/) (2026)
- [EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting](https://mlsanity.com/paper/2605.16022/) (2026)
- [Tempered Self-Similarity Alignment for Physically Plausible Video Generation](https://mlsanity.com/paper/2605.24962/) (2026)
- [CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction](https://mlsanity.com/paper/2605.30239/) (2026)
- [Streaming Video Generation with Streaming Force Control](https://mlsanity.com/paper/2606.07508/) (2026)
- [Adaptive Volumetric Mechanical Property Fields Invariant to Resolution](https://mlsanity.com/paper/2606.18231/) (2026)
- [ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors](https://mlsanity.com/paper/2603.04338/) (2026)

## Abstract (arXiv)

Realistic simulation of dynamic scenes requires accurately capturing diverse material properties and modeling complex object interactions grounded in physical principles. However, existing methods are constrained to basic material types with limited predictable parameters, making them insufficient to represent the complexity of real-world materials. We introduce PhysFlow, a novel approach that leverages multi-modal foundation models and video diffusion to achieve enhanced 4D dynamic scene simulation. Our method utilizes multi-modal models to identify material types and initialize material parameters through image queries, while simultaneously inferring 3D Gaussian splats for detailed scene representation. We further refine these material parameters using video diffusion with a differentiable Material Point Method (MPM) and optical flow guidance rather than render loss or Score Distillation Sampling (SDS) loss. This integrated framework enables accurate prediction and realistic simulation of dynamic interactions in real-world scenarios, advancing both accuracy and flexibility in physics-based simulations.