Research map / 3D vision / NeRF and radiance fields
Inferring Hybrid Neural Fluid Fields from Videos
Hong-Xing Yu, Yang Zheng, Yuan Gao, Yitong Deng, Bo Zhu, Jiajun Wu
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 HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Novel view synthesis | PSNR: 29.55 -> 31.14 | Improved |
| Use HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Novel view synthesis | LPIPS: 0.0881 -> 0.0966 | Hurt |
| Use HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Re-simulation | PSNR: 24.97 -> 28.37 | Improved |
| Use HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Re-simulation | LPIPS: 0.1278 -> 0.1171 | Improved |
| Use HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Future prediction | PSNR: 24.19 -> 26.12 | Improved |
| Use HyFluid instead of PINF | Fluid reconstruction on ScalarFlow real captures · Future prediction | LPIPS: 0.2155 -> 0.1968 | Improved |
| Add laminar regularization loss (ablation) | Naive HyFluid using rendering and density losses · Fluid velocity recovery and re-simulation | re-simulation quality | Improved |
| Add projection loss (ablation) | HyFluid with laminar regularization · Fluid velocity recovery and re-simulation | re-simulation quality | Improved |
| Add vortex particle-driven residual velocity (ablation) | HyFluid with physics-based losses · Fluid velocity recovery and re-simulation | re-simulation quality | Improved |
| Use only a pointwise divergence penalty instead of pressure projection (ablation) | HyFluid velocity learning · Fluid velocity recovery | velocity quality | Hurt |
| Use spatially varying learned radiance instead of constant radiance (ablation) | HyFluid appearance and density inference · Sparse-view fluid reconstruction | reconstruction quality | No clear effect |
Closest papers by meaning
- NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields (ICML 2022 · similarity 0.89)
- PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction (ICML 2025 · similarity 0.88)
- FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video (CVPR 2025 · similarity 0.87)
- HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction (ICML 2024 · similarity 0.86)
- FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity (CVPR 2025 · similarity 0.85)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.85)
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.
