Research map / Probabilistic and scientific modeling / Dynamical systems
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
Shanyan Guan, Huayu Deng, Yunbo Wang, Xiaokang Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use image-supervised NeuroFluid instead of DLF | DLF particle transition model · WaterCube, WaterSphere, and HoneyCone grounding | average particle distance: 32.3 -> 28.8; 32.2 -> 31.1; 61.5 -> 30.9 | Improved |
| use image-supervised NeuroFluid instead of DLF | DLF particle transition model · WaterCube, WaterSphere, and HoneyCone future prediction | average particle distance: 47.4 -> 35.5; 48.1 -> 30.7; 69.7 -> 54.2 | Improved |
| use PhysNeRF in place of the compared neural renderers | novel-view synthesis · WaterCube, WaterSphere, and HoneyCone, observed frames | PSNR: 30.08 -> 30.76; 28.80 -> 33.24; 31.02 -> 37.82 | Improved |
| use PhysNeRF in place of the compared neural renderers | novel-view synthesis · WaterCube, WaterSphere, and HoneyCone, future frames | PSNR: 27.28 -> 28.50; 26.95 -> 28.69; 23.25 -> 29.69 | Improved |
| add the fictitious particle center encoding (ablation) | PhysNeRF · WaterCube | average particle distance, grounding: 37.2 -> 28.8 | Improved |
| add the fictitious particle center encoding (ablation) | PhysNeRF · WaterCube | average particle distance, prediction: 41.3 -> 35.5 | Improved |
| add the sphere density encoding (ablation) | PhysNeRF · WaterCube | average particle distance, grounding: 31.2 -> 28.8 | Improved |
| add the sphere density encoding (ablation) | PhysNeRF · WaterCube | average particle distance, prediction: 39.3 -> 35.5 | Improved |
| add the deformation vector encoding (ablation) | PhysNeRF · WaterCube | average particle distance, grounding: 33.0 -> 28.8 | Improved |
| add the deformation vector encoding (ablation) | PhysNeRF · WaterCube | average particle distance, prediction: 40.5 -> 35.5 | Improved |
| add the particle-relative direction encoding (ablation) | PhysNeRF · WaterCube | average particle distance, grounding: 32.2 -> 28.8 | Improved |
| add the particle-relative direction encoding (ablation) | PhysNeRF · WaterCube | average particle distance, prediction: 43.9 -> 35.5 | Improved |
Later papers that compared with this method
1 later accepted paper reports NeuroFluid as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video (ICLR 2024 · better on 2 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics (NeurIPS 2024 · similarity 0.87)
- PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling (ICML 2024 · similarity 0.86)
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics (ICML 2024 · similarity 0.86)
- HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction (ICML 2024 · similarity 0.86)
- Space and time continuous physics simulation from partial observations (ICLR 2024 · similarity 0.86)
- Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
