Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis
Designing a network on 3D surface for non-rigid shape analysis is a challenging task. In this work, we propose a novel spectral transform network on 3D surface to learn shape descriptors. The proposed network architecture consists of four stages: raw descriptor extraction, surface second-order pooling, mixture of power function-based spectral transform, and metric learning. The proposed network is simple and shallow. Quantitative experiments on challenging benchmarks show its effectiveness for non-rigid shape retrieval and classification, e.g., it achieved the highest accuracies on SHREC14, 15 datasets as well as the Range subset of SHREC17 dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMetric LearningRetrievalSimilar Papers 제목 키워드 기반
A Statistical Model of Riemannian Metric Variation for Deformable Shape Analysis
The analysis of deformable 3D shape is often cast in terms of the shape's intrinsic geometry due to its invariance to a wide range of non-rigid deformations. However, object's plasticity in non-rigid transformation ofte…
RetrievalOn Nonrigid Shape Similarity and Correspondence
An important operation in geometry processing is finding the correspondences between pairs of shapes. The Gromov-Hausdorff distance, a measure of dissimilarity between metric spaces, has been found to be highly useful fo…
A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures
Constructing a robust and discriminative local descriptor for 3D shape is a key component of many computer vision applications. Although existing learning-based approaches can achieve good performance in some specific be…
TripletSymmetry-Aware Nonrigid Matching of Incomplete 3D Surfaces
We present a nonrigid shape matching technique for establishing correspondences of incomplete 3D surfaces that exhibit intrinsic reflectional symmetry. The key for solving the symmetry ambiguity problem is to use a point…
Graph MatchingMedial Spectral Coordinates for 3D Shape Analysis
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects represented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has b…
Autonomous DrivingObject