PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation

• URL: http://arxiv.org/abs/2511.18570v1
• Date: Sun, 23 Nov 2025 18:29:20 GMT
• Title: PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
• Authors: Samarth Chopra, Jing Liang, Gershom Seneviratne, Dinesh Manocha,
• Abstract summary: We present PhysGS, a Bayesian-inferred extension of 3D Gaussian Splatting that estimates dense, per-point physical properties from visual cues and vision-language priors.<n>Across object-scale, indoor, and outdoor real-world datasets, PhysGS improves accuracy of the mass estimation by up to 22.8%.<n>Our results demonstrate that PhysGS unifies 3D reconstruction, uncertainty modeling, and physical reasoning in a single, spatially continuous framework.
• Score: 42.995383993323635
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding physical properties such as friction, stiffness, hardness, and material composition is essential for enabling robots to interact safely and effectively with their surroundings. However, existing 3D reconstruction methods focus on geometry and appearance and cannot infer these underlying physical properties. We present PhysGS, a Bayesian-inferred extension of 3D Gaussian Splatting that estimates dense, per-point physical properties from visual cues and vision--language priors. We formulate property estimation as Bayesian inference over Gaussian splats, where material and property beliefs are iteratively refined as new observations arrive. PhysGS also models aleatoric and epistemic uncertainties, enabling uncertainty-aware object and scene interpretation. Across object-scale (ABO-500), indoor, and outdoor real-world datasets, PhysGS improves accuracy of the mass estimation by up to 22.8%, reduces Shore hardness error by up to 61.2%, and lowers kinetic friction error by up to 18.1% compared to deterministic baselines. Our results demonstrate that PhysGS unifies 3D reconstruction, uncertainty modeling, and physical reasoning in a single, spatially continuous framework for dense physical property estimation. Additional results are available at https://samchopra2003.github.io/physgs.

Related papers

• Measuring Physical Plausibility of 3D Human Poses Using Physics Simulation [19.26289173517333]
  We introduce two metrics to capture the physical plausibility and stability of predicted 3D poses from any 3D Human Pose Estimation model.<n>Using physics simulation, we discover correlations with existing plausibility metrics and measuring stability during motion.
  arXiv  Detail & Related papers  (2025-02-06T20:15:49Z)
• OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation [25.790371838717284]
  We propose OmniPhysGS for synthesizing a physics-based 3D dynamic scene composed of more general objects.<n>Our method surpasses existing methods by approximately 3% to 16% in metrics of visual quality and text alignment.
  arXiv  Detail & Related papers  (2025-01-31T09:28:07Z)
• GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs [21.3615403516602]
  Estimating physical properties for visual data is a crucial task in computer vision, graphics, and robotics.<n>We introduce GaussianProperty, a training-free framework that assigns physical properties of materials to 3D Gaussians.<n>We demonstrate that 3D Gaussians with physical property annotations enable applications in physics-based dynamic simulation and robotic grasping.
  arXiv  Detail & Related papers  (2024-12-15T17:44:10Z)
• Compositional Physical Reasoning of Objects and Events from Videos [122.6862357340911]
  This paper addresses the challenge of inferring hidden physical properties from objects' motion and interactions.<n>We evaluate state-of-the-art video reasoning models on ComPhy and reveal their limited ability to capture these hidden properties.<n>We also propose a novel neuro-symbolic framework, Physical Concept Reasoner (PCR), that learns and reasons about both visible and hidden physical properties.
  arXiv  Detail & Related papers  (2024-08-02T15:19:55Z)
• 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)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties [100.19685489335828]
  This work proposes a novel dataset and benchmark, termed Physion++, to rigorously evaluate visual physical prediction in artificial systems. We test scenarios where accurate prediction relies on estimates of properties such as mass, friction, elasticity, and deformability. We evaluate the performance of a number of state-of-the-art prediction models that span a variety of levels of learning vs. built-in knowledge, and compare that performance to a set of human predictions.
  arXiv  Detail & Related papers  (2023-06-27T17:59:33Z)
• Visual Grounding of Learned Physical Models [66.04898704928517]
  Humans intuitively recognize objects' physical properties and predict their motion, even when the objects are engaged in complicated interactions. We present a neural model that simultaneously reasons about physics and makes future predictions based on visual and dynamics priors. Experiments show that our model can infer the physical properties within a few observations, which allows the model to quickly adapt to unseen scenarios and make accurate predictions into the future.
  arXiv  Detail & Related papers  (2020-04-28T17:06:38Z)

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.