CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations

• URL: http://arxiv.org/abs/2605.10586v1
• Date: Mon, 11 May 2026 13:59:01 GMT
• Title: CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations
• Abstract summary: CausalGS is a framework that learns the causal dynamics of complex dynamic 3D scenes solely from multi-view videos.<n>Our work shows that, without any human annotation, the model is able to learn the complex interactions between multiple physical properties.
• Score: 0.3580891736370874
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning a physical model from video data that can comprehend physical laws and predict the future trajectories of objects is a formidable challenge in artificial intelligence. Prior approaches either leverage various Partial Differential Equations (PDEs) as soft constraints in the form of PINN losses, or integrate physics simulators into neural networks; however, they often rely on strong priors or high-quality geometry reconstruction. In this paper, we propose CausalGS, a framework that learns the causal dynamics of complex dynamic 3D scenes solely from multi-view videos, while dispensing with the reliance on explicit priors. At its core is an inverse physics inference module that decouples the complex dynamics problem from the video into the joint inference of two factors: the initial velocity field representing the scene's kinematics, and the intrinsic material properties governing its dynamics. This inferred physical information is then utilized within a differentiable physics simulator to guide the learning process in a physics-regularized manner. Extensive experiments demonstrate that CausalGS surpasses the state-of-the-art on the highly challenging task of long-term future frame extrapolation, while also exhibiting advanced performance in novel view interpolation. Crucially, our work shows that, without any human annotation, the model is able to learn the complex interactions between multiple physical properties and understand the causal relationships driving the scene's dynamic evolution, solely from visual observations.

Related papers

• Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos [2.5608298830470013]
  Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world.<n>We propose Analytic Dynamics, a feed-forward dynamics inference framework that introduces an intermediate physics-grounded dynamics representation.
  arXiv  Detail & Related papers  (2026-08-31T16:08:04Z)
• VeloGauss: Learning Physically Consistent Gaussian Velocity Fields from Videos [11.004005265944706]
  VeloGauss is designed to learn the physical properties of complex dynamic 3D scenes without physical priors.<n>Our method learns the velocity field for each Gaussian particle by introducing a Physics Code and a Particle Dynamics System.
  arXiv  Detail & Related papers  (2026-05-11T13:38:14Z)
• PhyCo: Learning Controllable Physical Priors for Generative Motion [55.59209981836171]
  We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation.<n>Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback.
  arXiv  Detail & Related papers  (2026-04-30T17:53:03Z)
• PhysInOne: Visual Physics Learning and Reasoning in One Suite [41.08902311182402]
  We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems.<n>Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2 million videos across 153,810 dynamic 3D scenes.<n>We demonstrate PhysInOne's efficacy across four emerging applications: physics-aware video generation, long-/short-term future frame prediction, physical property estimation, and motion transfer.
  arXiv  Detail & Related papers  (2026-04-10T15:27:27Z)
• MMPhysVideo: Scaling Physical Plausibility in Video Generation via Joint Multimodal Modeling [55.72785604682579]
  MMPhysVideo is a framework to scale physical plausibility in video generation in joint multimodal modeling.<n>MMPhysVideo consistently improves physical plausibility and visual quality over advanced models across various benchmarks.
  arXiv  Detail & Related papers  (2026-04-03T07:32:24Z)
• PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment [23.066204478030627]
  Video Models (VDMs) offer a promising approach for simulating dynamic scenes and environments.<n>Existing models often generate temporally incoherent content that violates basic physical intuition.<n>We propose PhysAlign, an efficient framework for physics-coherent image-to-videoI (2V) generation.
  arXiv  Detail & Related papers  (2026-03-14T05:44:18Z)
• PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View Synthesis [62.283499219361595]
  PhysGaia is a physics-aware dataset specifically designed for Dynamic Novel View Synthesis (DyNVS)<n>Our dataset provides complex dynamic scenarios with rich interactions among multiple objects.<n>PhysGaia will significantly advance research in dynamic view synthesis, physics-based scene understanding, and deep learning models integrated with physical simulation.
  arXiv  Detail & Related papers  (2025-06-03T12:19:18Z)
• Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics [6.675805308519987]
  We introduce a novel framework for modeling rigid body dynamics and learning collision interactions.<n>We propose a physics-informed message-passing neural architecture, embedding physical laws directly in the model.<n>This work addresses the challenge of multi-entity dynamic interactions, with applications spanning diverse scientific and engineering domains.
  arXiv  Detail & Related papers  (2024-11-18T11:03:15Z)
• Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video [58.043569985784806]
  We introduce latent intuitive physics, a transfer learning framework for physics simulation. It can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. We validate our model in three ways: (i) novel scene simulation with the learned visual-world physics, (ii) future prediction of the observed fluid dynamics, and (iii) supervised particle simulation.
  arXiv  Detail & Related papers  (2024-06-18T16:37:44Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language [92.7638697243969]
  We propose a unified framework that can jointly learn visual concepts and infer physics models of objects from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
  arXiv  Detail & Related papers  (2021-10-28T17:59:13Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.