In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3% on ModelNet40, and are more robust to geometric transformations.
The discovery of natural adhesion phenomena and mechanisms has advanced the development of a new generation of tissue adhesives in recent decades. In this study, we develop a natural biological adhesive from snail mucus gel, which consists a network of positively charged protein and polyanionic glycosaminoglycan. The malleable bulk adhesive matrix can adhere to wet tissue through multiple interactions. The biomaterial exhibits excellent haemostatic activity, biocompatibility and biodegradability, and it is effective in accelerating the healing of full-thickness skin wounds in both normal and diabetic male rats. Further mechanistic study shows it effectively promotes the polarization of macrophages towards the anti-inflammatory phenotype, alleviates inflammation in chronic wounds, and significantly improves epithelial regeneration and angiogenesis. Its abundant heparin-like glycosaminoglycan component is the main active ingredient. These findings provide theoretical and material insights into bio-inspired tissue adhesives and bioengineered scaffold designs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.