Sphere Image for 3-D Model Retrieval

Ding, Ke; Liu, Yunhui

doi:10.1109/tmm.2014.2314073

Cited by 6 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Ding and Liu [45] defined a view based shape descrip tor named Sphere Image that integrates the spatial information of a collection of viewpoints and their corresponding view features that are matched based on a probabilistic graphical model. Similar to the Sphere Image, Bonaventura et al [46] proposed a 3D shape descriptor of the Information Sphere and utilized mutual informa tion based measures for the matching, whereas Li et al [47] designed a feature named Spherical SIFT to represent the salient local features on spherical images.…”

Section: View Based Techniquesmentioning

confidence: 99%

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

et al. 2015

Computer Vision and Image Understanding

118

View full text Add to dashboard Cite

a b s t r a c tLarge scale 3D shape retrieval has become an important research direction in content based 3D shape retrieval. To promote this research area, two Shape Retrieval Contest (SHREC) tracks on large scale com prehensive and sketch based 3D model retrieval have been organized by us in 2014. Both tracks were based on a unified large scale benchmark that supports multimodal queries (3D models and sketches). This benchmark contains 13680 sketches and 8987 3D models, divided into 171 distinct classes. It was compiled to be a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domain specific model types. Twelve and six distinct 3D shape retrieval methods have competed with each other in these two contests, respectively. To measure and compare the performance of the participating and other promising Query by Model or Query by Sketch 3D shape retrieval methods and to solicit state of the art approaches, we perform a more comprehensive comparison of twenty six (eighteen originally participating algorithms and eight additional state of the art or new) retrieval methods by evaluating them on the common benchmark. The benchmark, results, and evaluation tools are publicly available at our websites

show abstract

Section: View Based Techniquesmentioning

confidence: 99%

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

et al. 2015

Computer Vision and Image Understanding

118

View full text Add to dashboard Cite

show abstract

“…Many approaches based on 3D Shape descriptors were proposed [7]. Extended Gaussian Images [8][9] were frequently used, based on a mapping of normal surface of an object onto the unit sphere (Gaussian sphere.) extended to include areas of each face.…”

Section: Introductionmentioning

confidence: 99%

“…In the 2D/3D approach a 3D object is represented by a set of 2D view (they use a large dataset of 2D views). Features are extracted among the different single-view [9].…”

Section: Introductionmentioning

confidence: 99%

“…K. Ding et al [9] propose a 3D model descriptor called Sphere Image, which is defined as a collection of view features. The model is an improvement of the characteristic views approaches.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we use a system based on the extraction of features by the calculation of the geodesic distance [9] on a mesh using an iterative algorithm for solving the Eikonal equation. For good classification results we adopt M-SVM to achieve excellent recognition rates in experiment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D Objects Retrieval using Geodesic Distance Based on Eikonal equation

Naji¹,

Fakir²,

Bencharef³

2015

TIJEE

View full text Add to dashboard Cite

Recently, shape-based matching and retrieval of 3D polygonal models has become one of the most fundamental problems in computer vision. Dealing with families of objects instead of a single one may impose further challenges on regular geometric algorithms. In this paper we focus on the classification of 3D objects based on their geodesic distance & path calculated on a mesh using an iterative algorithm for solving the Eikonal equation. For the classification process, we use both Multiclass Support Vector Machine (M-SVM) classifier,K-Nearest Neighbors (KNN), Decision Tree (DT) and Artificial Neural Networks (ANN) to better evaluate our descriptors. We illustrate the potential of extracted characteristics by two 3D benchmarks. The recognition rates achieved in all experiments show that a small number of curve between 9 and 12 can correctly categorize a family of 3D objects.

show abstract

MVHANet: multi-view hierarchical aggregation network for skeleton-based hand gesture recognition

Liu

Duan

et al. 2023

SIViP

View full text Add to dashboard Cite

Skeleton-based gesture recognition (SHGR) is a very challenging task due to the complex articulated topology of hands.Previous works often learn hand characteristics from a single observation viewpoint. However, the spatial structure of the hand skeletons cannot be investigated explicitly, and various context information hidden in multiple viewpoints is disregarded. To resolve this issue, we propose a novel multi-view hierarchical aggregation network (MVHANet) for SHGR, which is composed of three parts. Firstly, two-dimensional non-uniform spatial sampling (2DNUSS), a novel strategy forming extrinsic parameter distributions of virtual cameras, is presented to enumerate viewpoints to observe hand skeletons from reasonable directions. Afterwards, we adopt coordinate transformation to generate multi-view hand skeletons and employ a multi-branch convolutional neural networks (CNNs) to further extract the multi-view features of hand skeletons.Furthermore, we exploit a novel hierarchical aggregation network including hierarchical attention architecture (HAA) and global context modeling (GCM) to fuse the multi-view features. Specifically, the HAA is composed of view level and group level for learning the local correlation and discriminative weights of multiple views; GCM is aimed to capture the global information of all the views from each level. Finally, the outputs of HAA and GCM are combined for hand gesture classification. In this way, we fully leverage the multi-view information of hand skeletons and improve the performance of recognition. We conduct extensive experiments on publicly available SHREC'17 Track dataset, DHG-14/28 dataset and First-Person Dynamic Hand Actions dataset. Experimental results demonstrate that our work can be competitive with the state-of-the-art methods.

show abstract

Sphere Image for 3-D Model Retrieval

Cited by 6 publications

References 35 publications

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

3D Objects Retrieval using Geodesic Distance Based on Eikonal equation

MVHANet: multi-view hierarchical aggregation network for skeleton-based hand gesture recognition

Contact Info

Product

Resources

About