Skeletal Point Representations with Geometric Deep Learning

Autor:	Khargonkar, Ninad, Paniagua, Beatriz, Vicory, Jared
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Skeletonization has been a popular shape analysis technique that models both the interior and exterior of an object. Existing template-based calculations of skeletal models from anatomical structures are a time-consuming manual process. Recently, learning-based methods have been used to extract skeletons from 3D shapes. In this work, we propose novel additional geometric terms for calculating skeletal structures of objects. The results are similar to traditional fitted s-reps but but are produced much more quickly. Evaluation on real clinical data shows that the learned model predicts accurate skeletal representations and shows the impact of proposed geometric losses along with using s-reps as weak supervision. Comment: 5 pages, 5 figures, 2 tables. Accepted to IEEE International Symposium on Biomedical Imaging (ISBI) 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.02123 Zobrazit plný text záznamu View this record from Arxiv