mlsanityData to 7 Oct 2026

NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields

arXiv 2203.01762 ↗First posted 3 Mar 2022cs.LG cs.CV physics.flu-dyncited by 36

Not on the map. Why?

Abstract (arXiv)

Deep learning has shown great potential for modeling the physical dynamics of complex particle systems such as fluids. Existing approaches, however, require the supervision of consecutive particle properties, including positions and velocities. In this paper, we consider a partially observable scenario known as fluid dynamics grounding, that is, inferring the state transitions and interactions within the fluid particle systems from sequential visual observations of the fluid surface. We propose a differentiable two-stage network named NeuroFluid. Our approach consists of (i) a particle-driven neural renderer, which involves fluid physical properties into the volume rendering function, and (ii) a particle transition model optimized to reduce the differences between the rendered and the observed images. NeuroFluid provides the first solution to unsupervised learning of particle-based fluid dynamics by training these two models jointly. It is shown to reasonably estimate the underlying physics of fluids with different initial shapes, viscosity, and densities.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 23 of its 51 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

23 of 51 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  5. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  8. 2017Neural 3D Mesh Renderercited by 437
  9. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  10. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  11. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  12. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
11 more
  1. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  2. 2020Learning to Control PDEs with Differentiable Physicscited by 131
  3. 2018Deep Fluids: A Generative Network for Parameterized Fluid Simulationscited by 121
  4. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  5. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  6. 2018Flexible Neural Representation for Physics Predictioncited by 91
  7. 2018SPNets: Differentiable Fluid Dynamics for Deep Neural Networkscited by 62
  8. 2020Visual Grounding of Learned Physical Modelscited by 54
  9. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  10. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  11. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 10; 2025: 12; 2026: 4.

36 papers.

Sort:

  1. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  2. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 145
  3. 2024Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussianscited by 92
  4. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 78
  5. 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 30
  6. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  7. 2022ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fieldscited by 27
  8. 2025Generative Physical AI in Vision: A Surveycited by 24
  9. 2023Inferring Hybrid Neural Fluid Fields from Videoscited by 18
  10. 2023Learning Vortex Dynamics for Fluid Inference and Predictioncited by 17
  11. 2023Learning 3D Particle-based Simulators from RGB-D Videoscited by 17
  12. 2024Disco4D: Disentangled 4D Human Generation and Animation from a Single Imagecited by 17
24 more
  1. 2024Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimizationcited by 16
  2. 2025DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interactioncited by 16
  3. 2022Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fieldscited by 15
  4. 2026PhysInOne: Visual Physics Learning and Reasoning in One Suitecited by 9
  5. 2024Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Videocited by 8
  6. 2025MASIV: Toward Material-Agnostic System Identification from Videoscited by 7
  7. 2023Dynamic Appearance Particle Neural Radiance Fieldcited by 6
  8. 2024Scaling Face Interaction Graph Networks to Real World Scenescited by 5
  9. 2025ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolationcited by 5
  10. 2024Dynamic Scene Understanding through Object-Centric Voxelization and Neural Renderingcited by 4
  11. 2024DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Renderingcited by 4
  12. 2024Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Modelcited by 4
  13. 2025ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimationcited by 4
  14. 2023Inferring Fluid Dynamics via Inverse Renderingcited by 3
  15. 2023DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelizationcited by 3
  16. 2025Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Timecited by 3
  17. 2025VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimizationcited by 3
  18. 2025Structure from Collisioncited by 1
  19. 2025Learning an Implicit Physics Model for Image-based Fluid Simulationcited by 1
  20. 2025WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wildcited by 1
  21. 2025NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfoldingcited by 1
  22. 2026CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditionscited by 0
  23. 2026LASER: Learning Active Sensing for Continuum Field Reconstructioncited by 0
  24. 2026SplashSplat: Reconstructing Splashing Liquids from Real-World Multi-View Videoscited by 0