MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling
Researchers have introduced MambaH-Fit, a new framework for point cloud normal estimation that utilizes state space models (SSMs). This approach aims to improve the modeling of fine-grained geometric structures, which current methods often struggle with. The framework incorporates an Attention-driven Hierarchical Feature Fusion scheme to enhance geometric context learning and a Patch-wise State Space Model to treat point cloud patches as implicit hyper-surfaces for better geometric understanding. AI