Aug 2026
A visual Mamba-based global-local framework for instance segmentation of highly overlapping multi-scale bubbles in dense two-phase flows
A global-local fusion segmentation model named global-local bubble network is designed, which uses the visual state space encoder as the backbone for feature extraction and establishes long-range pixel dependencies, significantly enhancing context inference capabilities under dense occlusion.
Mi Wang, Kai-Jie Tong, Xin-Xin Li et al.
· The Physics of Fluids · 0 citations