Tao, NingxiaoZhang, LiruNi, XingyuChu, MengyuChen, BaoquanChristie, MarcPietroni, NicoWang, Yu-Shuen2025-10-072025-10-0720251467-8659https://doi.org/10.1111/cgf.70274https://diglib.eg.org/handle/10.1111/cgf70274We present FlowCapX, a physics-enhanced framework for flow reconstruction from sparse video inputs, addressing the challenge of jointly optimizing complex physical constraints and sparse observational data over long time horizons. Existing methods often struggle to capture turbulent motion while maintaining physical consistency, limiting reconstruction quality and downstream tasks. Focusing on velocity inference, our approach introduces a hybrid framework that strategically separates representation and supervision across spatial scales. At the coarse level, we resolve sparse-view ambiguities via a novel optimization strategy that aligns long-term observation with physics-grounded velocity fields. By emphasizing vorticity-based physical constraints, our method enhances physical fidelity and improves optimization stability. At the fine level, we prioritize observational fidelity to preserve critical turbulent structures. Extensive experiments demonstrate state-of-the-art velocity reconstruction, enabling velocity-aware downstream tasks, e.g., accurate flow analysis, scene augmentation with tracer visualization and re-simulation. Our implementation is released at https://github.com/taoningxiao/FlowCapX.git.CCS Concepts: Computing methodologies → Physical simulation; Neural networksComputing methodologies → Physical simulationNeural networks10.1111/cgf.7027410 pages