Research map / Probabilistic and scientific modeling / Differential equations and PDEs
ELHINN: Unifying Dense Crowd Simulation Across Scales via Eulerian–Lagrangian Hydrodynamics
Yanshan Zhou, Pingrui Lai, Jiaqi Yu, Cunyan Li, Hua Yang, Xiaoyun Zhang
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 |
|---|---|---|---|
| add boundary conditions (ablation) | HINN++ · DCFD velocity evolution | FID: 0.0395 -> 0.0278 | Improved |
| add boundary conditions (ablation) | HINN++ · DCFD velocity evolution | SSIM: 0.4837 -> 0.6030 | Improved |
| add boundary conditions (ablation) | HINN++ · DCFD velocity evolution | IS: 1.7883 -> 1.7469 | Hurt |
| add KAN residual correction (ablation) | HINN++ · DCFD velocity evolution | FID: 0.0350 -> 0.0278 | Improved |
| add KAN residual correction (ablation) | HINN++ · DCFD velocity evolution | SSIM: 0.6019 -> 0.6030 | No clear effect |
| use KAN instead of MLP for residual correction (ablation) | HINN++ · DCFD velocity evolution | FID: 0.0382 -> 0.0278 | Improved |
| add collision-avoidance loss (ablation) | PINN · MOT20 trajectory refinement | JADE: 8.293 -> 8.274 | Improved |
| add MLP predictive network instead of direct integration (ablation) | PINN · MOT20 trajectory refinement | JADE: 8.307 -> 8.274 | Improved |
| add entrance-aware resampling (EARS) (ablation) | PINN · MOT20 trajectory refinement | JADE: 13.257 -> 8.274 | Improved |
| add entrance-aware resampling (EARS) (ablation) | PINN · MOT20 trajectory refinement | JFDE: 17.438 -> 12.836 | Improved |
| use HINN++ instead of HINN for velocity evolution | ELHINN · DCFD velocity evolution | SSIM: 0.4782 -> 0.6030 | Improved |
| use evolved Eulerian velocity prior with PINN instead of microscopic baselines | ELHINN · MOT20 trajectory refinement | JADE: 9.231 (PCS) -> 8.274 | Improved |
Closest papers by meaning
- Learning Extremely High Density Crowds as Active Matters (CVPR 2025 · similarity 0.85)
- Lagrangian Flow Networks for Conservation Laws (ICLR 2024 · similarity 0.84)
- Social Physics Informed Diffusion Model for Crowd Simulation (AAAI 2024 · similarity 0.84)
- Space and time continuous physics simulation from partial observations (ICLR 2024 · similarity 0.83)
- Continuous Locomotive Crowd Behavior Generation (CVPR 2025 · similarity 0.83)
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics (ICML 2024 · similarity 0.83)
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.
