Structural information, and thus achieve accurate results on the task ofįine-grained 3D object retrieval. Novel deep architecture, RISA-Net, which learns rotation invariant 3D shapeĭescriptors that are capable of encoding fine-grained geometric information and Systems fail to meet the above two criteria. The shape descriptions used in existing 3D shape retrieval Moreover, 3D objectsĬan be placed with arbitrary position and orientation in real-worldĪpplications, which further requires shape descriptors to be robust to rigid To discriminate shapes with globally similar structures. Shape descriptors to be capable of representing detailed geometric information Shape in a repository with models belonging to the same class, which requires Authors: Rao Fu, Jie Yang, Jiawei Sun, Fang-Lue Zhang, Yu-Kun Lai, Lin Gao Download PDF Abstract: Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |