mlsanityData to 14 Oct 2026

DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions

arXiv 1906.03853 ↗First posted 10 Jun 2019cs.RO cs.AI cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the object's static appearance. In this paper, we propose DensePhysNet, a system that actively executes a sequence of dynamic interactions (e.g., sliding and colliding), and uses a deep predictive model over its visual observations to learn dense, pixel-wise representations that reflect the physical properties of observed objects. Our experiments in both simulation and real settings demonstrate that the learned representations carry rich physical information, and can directly be used to decode physical object properties such as friction and mass. The use of dense representation enables DensePhysNet to generalize well to novel scenes with more objects than in training. With knowledge of object physics, the learned representation also leads to more accurate and efficient manipulation in downstream tasks than the state-of-the-art.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 6; 2023: 6; 2024: 10; 2025: 12; 2026: 13.

63 papers.

Sort:

By area:

  1. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
  2. 2026Causal World Modeling for Robot Controlcited by 321
  3. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  4. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 174
  5. 2023Physically Grounded Vision-Language Models for Robotic Manipulationcited by 165
  6. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 154
  7. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 144
  8. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  9. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 87
  10. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 80
  11. 2021AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactionscited by 57
  12. 2024AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulationcited by 54
38 more
  1. 2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 51
  2. 2024GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulationcited by 49
  3. 2021O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learningcited by 46
  4. 2021Act the Part: Learning Interaction Strategies for Articulated Object Part Discoverycited by 45
  5. 2024Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modelingcited by 43
  6. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 36
  7. 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 34
  8. 2021Learning Models as Functionals of Signed-Distance Fields for Manipulation Planningcited by 29
  9. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 28
  10. 2021Block Contextual MDPs for Continual Learningcited by 25
  11. 2021SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulationcited by 24
  12. 2025Generative Physical AI in Vision: A Surveycited by 24
  13. 2021HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworkscited by 18
  14. 2021Pushing it out of the Way: Interactive Visual Navigationcited by 16
  15. 2024Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimizationcited by 16
  16. 2025Think Before You Diffuse: Infusing Physical Rules into Video Diffusioncited by 16
  17. 20233D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenescited by 12
  18. 2024PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Modelscited by 11
  19. 2022Inferring Articulated Rigid Body Dynamics from RGBD Videocited by 10
  20. 2022EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamicscited by 10
  21. 2022Cascaded Compositional Residual Learning for Complex Interactive Behaviorscited by 10
  22. 2025PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesiscited by 10
  23. 2021IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenescited by 9
  24. 2025MASIV: Toward Material-Agnostic System Identification from Videoscited by 9
  25. 2024Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Videocited by 8
  26. 2022Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objectscited by 7
  27. 2026MOSIV: Multi-Object System Identification from Videoscited by 6
  28. 2021Object and Relation Centric Representations for Push Effect Predictioncited by 5
  29. 2023Perceiving Unseen 3D Objects by Poking the Objectscited by 5
  30. 2025Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalizationcited by 5
  31. 2025Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulationcited by 5
  32. 2025NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videoscited by 5
  33. 2025ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimationcited by 4
  34. 2026D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Graspingcited by 3
  35. 2026NeuROK: Generative 4D Neural Object Kinematicscited by 3
  36. 2026What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representationscited by 3
  37. 2021A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulationcited by 2
  38. 2026Learning Physics-Guided Residual Dynamics for Deformable Object Simulationcited by 2

50 most cited of 63 All 63 (JSON)