AINeutralarXiv – CS AI · 15h ago6/10
🧠
FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives
Researchers introduce FLUIDSPLAT, a neural network model that reconstructs continuous flow fields from sparse sensor data using anisotropic Gaussian primitives. The approach provides theoretical guarantees on approximation rates and demonstrates 11-28% error improvements over existing methods across multiple aerodynamic benchmarks.