STDDN integrates the fluid continuity equation into a Neural ODE with density-velocity graph learning to improve long-term crowd trajectory prediction and reduce inference latency.
In contrast, while the SPDiff method is capable of 18 Published as a conference paper at ICLR 2026 Table 9: Additional performance comparison on ETH and HOTEL datasets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation
STDDN integrates the fluid continuity equation into a Neural ODE with density-velocity graph learning to improve long-term crowd trajectory prediction and reduce inference latency.