mlsanityData to 14 Oct 2026

PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation

arXiv 2511.18570 ↗First posted 23 Nov 2025cs.CV cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 47 of its 68 references that are in the map. First posted on arXiv 23 Nov 2025.

Builds on

47 of 68 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023Segment Anythingcited by 8,234
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  11. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  12. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
35 more
  1. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 559
  2. 2023LERF: Language Embedded Radiance Fieldscited by 543
  3. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  4. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  5. 2023ConceptFusion: Open-set Multimodal 3D Mappingcited by 304
  6. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 294
  7. 2020RELLIS-3D Dataset: Data, Benchmarks and Analysiscited by 119
  8. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 91
  9. 2024Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splattingcited by 82
  10. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66
  11. 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
  12. 2024Physical Property Understanding from Language-Embedded Feature Fieldscited by 48
  13. 2023NEWTON: Are Large Language Models Capable of Physical Reasoning?cited by 45
  14. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  15. 2021STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigationcited by 27
  16. 2024RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Drivingcited by 26
  17. 2022GrASPE: Graph based Multimodal Fusion for Robot Navigation in Unstructured Outdoor Environmentscited by 25
  18. 2025PUGS: Zero-shot Physical Understanding with Gaussian Splattingcited by 24
  19. 2024GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMscited by 23
  20. 2023EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomycited by 21
  21. 2024Modeling uncertainty for Gaussian Splattingcited by 19
  22. 2022These Maps Are Made For Walking: Real-Time Terrain Property Estimation for Mobile Robotscited by 12
  23. 2022ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Imagescited by 12
  24. 2023MEM: Multi-Modal Elevation Mapping for Robotics and Learningcited by 11
  25. 2024Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigationcited by 10
  26. 2024DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policiescited by 9
  27. 2024Bayesian NeRF: Quantifying Uncertainty with Volume Density for Neural Implicit Fieldscited by 9
  28. 2024PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terraincited by 8
  29. 2024You've Got to Feel It To Believe It: Multi-Modal Bayesian Inference for Semantic and Property Predictioncited by 7
  30. 2024AgriNeRF: Neural Radiance Fields for Agriculture in Challenging Lighting Conditionscited by 7
  31. 2022AdaptiveON: Adaptive Outdoor Local Navigation Method For Stable and Reliable Actionscited by 5
  32. 2024RoadRunner M&M -- Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigationcited by 5
  33. 2024CROSS-GAiT: Cross-Attention-Based Multimodal Representation Fusion for Parametric Gait Adaptation in Complex Terrainscited by 4
  34. 2025E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mappingcited by 2
  35. 2025Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latentscited by 1
  2. 2026EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Videocited by 0
  3. 2026KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representationscited by 0
  4. 2026Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videoscited by 0
  5. 2026PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussianscited by 0
  6. 2026PhysVGGT: Feed-Forward Dense Physical Property Estimation from A Single Imagecited by 0
  7. 2026From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Predictioncited by 0