Learning local shape descriptors for computing non-rigid dense correspondence

Learning local shape descriptors for computing non-rigid dense correspondence

Abstract A discriminative local shape descriptor plays an important role in various applications. In this paper, we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes. We use local “geometry images” to encode the multi-scale local features...

Full description

Bibliographic Details
Main Authors: Jianwei Guo, Hanyu Wang, Zhanglin Cheng, Xiaopeng Zhang, Dong-Ming Yan
Format: Article
Language:English
Published: SpringerOpen 2020-03-01
Series:Computational Visual Media
Subjects:
local feature descriptor
triplet CNN
dense correspondence
geometry image
non-rigid shape
Online Access:https://doi.org/10.1007/s41095-020-0163-y

Internet

https://doi.org/10.1007/s41095-020-0163-y

Similar Items