mlsanityData to 14 Oct 2026

SPNets: Differentiable Fluid Dynamics for Deep Neural Networks

arXiv 1806.06094 ↗First posted 15 Jun 2018cs.ROcited by 62

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce Smooth Particle Networks (SPNets), a framework for integrating fluid dynamics with deep networks. SPNets adds two new layers to the neural network toolbox: ConvSP and ConvSDF, which enable computing physical interactions with unordered particle sets. We use these lay- ers in combination with standard neural network layers to directly implement fluid dynamics inside a deep network, where the parameters of the network are the fluid parameters themselves (e.g., viscosity, cohesion, etc.). Because SPNets are imple- mented as a neural network, the resulting fluid dynamics are fully differentiable. We then show how this can be successfully used to learn fluid parameters from data, perform liquid control tasks, and learn policies to manipulate liquids.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 15; 2023: 8; 2024: 6; 2025: 5; 2026: 9.

62 papers.

Sort:

By area:

  1. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 103
  2. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  3. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 65
  4. 2021DiffPD: Differentiable Projective Dynamicscited by 62
  5. 2021Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contactcited by 52
  6. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  7. 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
  8. 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulationcited by 40
  9. 2021Efficient Differentiable Simulation of Articulated Bodiescited by 39
  10. 2021Spline-PINN: Approaching PDEs without Data using Fast, Physics-Informed Hermite-Spline CNNscited by 38
  11. 2022Physical Design using Differentiable Learned Simulatorscited by 37
  12. 2022NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fieldscited by 36
38 more
  1. 2022Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamicscited by 30
  2. 2021Boundary Graph Neural Networks for 3D Simulationscited by 24
  3. 2025Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physicscited by 20
  4. 2021Global Transport for Fluid Reconstruction with Learned Self-Supervisioncited by 18
  5. 2021SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learningcited by 16
  6. 2022Transformer with Implicit Edges for Particle-based Physics Simulationcited by 15
  7. 2021Direct Prediction of Steady-State Flow Fields in Meshed Domain with Graph Networkscited by 11
  8. 2021Physics perception in sloshing scenes with guaranteed thermodynamic consistencycited by 10
  9. 2022Thermodynamics of learning physical phenomenacited by 10
  10. 2021DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolationcited by 9
  11. 2022Fine-grained differentiable physics: a yarn-level model for fabricscited by 9
  12. 2022A Thermodynamics-informed Active Learning Approach to Perception and Reasoning about Fluidscited by 9
  13. 2024Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Videocited by 8
  14. 2021DQC: a Python program package for Differentiable Quantum Chemistrycited by 7
  15. 2023Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contactcited by 7
  16. 2021Learning to Manipulate Amorphous Materialscited by 5
  17. 2023Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervisioncited by 5
  18. 2023Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphicscited by 5
  19. 2021Image Based Reconstruction of Liquids from 2D Surface Detectionscited by 4
  20. 2022Learning Pair Potentials using Differentiable Simulationscited by 4
  21. 2024JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Frameworkcited by 4
  22. 20254D Gaussian Splatting as a Learned Dynamical Systemcited by 4
  23. 2022Half-Inverse Gradients for Physical Deep Learningcited by 3
  24. 2023SURFSUP: Learning Fluid Simulation for Novel Surfacescited by 3
  25. 2024DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Predictioncited by 3
  26. 2024Stabilizing Backpropagation Through Time to Learn Complex Physicscited by 3
  27. 2026WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformercited by 3
  28. 2026NeuROK: Generative 4D Neural Object Kinematicscited by 3
  29. 2021Differentiable model-based adaptive optics for two-photon microscopycited by 2
  30. 2021AbstractDifferentiation.jl: Backend-Agnostic Differentiable Programming in Juliacited by 2
  31. 2022Complex Locomotion Skill Learning via Differentiable Physicscited by 2
  32. 2022Wavelet-based Loss for High-frequency Interface Dynamicscited by 2
  33. 2024Bayesian Differentiable Physics for Cloth Digitalizationcited by 2
  34. 2026Neural Particle Automata: Learning Self-Organizing Particle Dynamicscited by 2
  35. 2022Control of Two-way Coupled Fluid Systems with Differentiable Solverscited by 1
  36. 2022Exploring Physical Latent Spaces for High-Resolution Flow Restorationcited by 1
  37. 2023Fluid Viscosity Prediction Leveraging Computer Vision and Robot Interactioncited by 1
  38. 2025Learning Particle Dynamics Subject to Rigid Body Manipulations Using Graph Neural Networkscited by 1

50 most cited of 62 All 62 (JSON)