Retrieval of non-rigid 3D shapes from multiple aspects

Kuang, Zhenzhong; Li, Zongmin; Jiang, Xiaxia; Liu, Yujie; Li, Hua

doi:10.1016/j.cad.2014.08.004

Cited by 18 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since there is no possibility to measure the ground truth, only precision is used as evaluation parameter and the same student group has performed the query and calculated the precision. The relevant image in the retrieval set is identified by the user who is performing the search and the same team is Further, the performance of the proposed object based similarity measure is evaluated on the above uncontrolled database and is compared with IRM [18] approach. The precision is shown below in Table 15 and it is observed from the result that the performance of the proposed similarity measure is high (around 20%-30%) compared to IRM.…”

Section: Resultsmentioning

confidence: 99%

“…The local shape descriptor is defined as a vector piecewise polynomial function of the geodesic radius of the intersect point through a simple approximation scheme. Kuang, et al, (2015) have addressed non-rigid 3D shape retrieval problem along with aspects such as shape representation, retrieval optimization and shape filtering. A new integration kernel based local descriptor and efficient voting scheme is designed for shape representation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FOSIR: Fuzzy-Object-Shape for Image Retrieval applications

2016

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

FOSIR: Fuzzy-Object-Shape for Image Retrieval applications

2016

View full text Add to dashboard Cite

“…However, one significant defect of traditional methods is that they usually lack of flexibility for model selection and parameter determination (e.g. the BOW model is limited to the roughly pre-defined dictionary), which may lead to the low effectiveness for shape representation [13]- [15]. In contrast, the recent deep learning technique is more suitable for data-driven model learning by providing labeled training data.…”

Section: Introductionmentioning

confidence: 99%

Revisit Point Cloud Recognition From the Viewpoint of Data Mixture

2020

Self Cite

View full text Add to dashboard Cite

In recent years, point cloud based data analysis has attracted lots of attentions of researchers from many different fields because of its simplicity and effectiveness. As a fundamental research, point cloud representation and recognition plays an important role. Although existing works achieved some good performances, they still cannot take full use of the information hidden in training data. This paper revisits the problem of point cloud representation and recognition from the viewpoint of data augmentation without incorporating additional data or more annotations. Different from existing works on 1D or 2D data, our proposed approach deals with a more complicated problem in three dimensional space for point cloud representation and recognition by mixing various training data from different object categories, which could help the classifier to better optimize the data-driven parameters. To validate the performance of our proposed approach, the popular used ModelNet40 dataset is employed as the standard benchmark. By carrying out comprehensive experiments under many different conditions, the experimental results show that our mixture method works positively towards improving the recognition performance of point cloud. INDEX TERMS Point cloud, deep learning, point cloud mixture, feature mixture.

show abstract

“…The increasing availability of 3D models makes an efficient retrieval system a key operation. 3D models are classfied into two main categories: rigid and non-rigid [7,21,28]. Especially the non-rigid 3D models are increasing steadily and used in many areas.…”

Section: Introductionmentioning

confidence: 99%

A non-rigid 3D model retrieval method based on scale-invariant heat kernel signature features

Ming

2016

Multimed Tools Appl

View full text Add to dashboard Cite

The number of non-rigid 3D models increases steadily in various areas. It is imperative to develop efficient retrieval system for 3D non-rigid models. As we know, global features fail to consistently describe the intra-class variability of non-rigid 3D models, the local features are more effective than global features for the retrieval of non-rigid 3D models. In this paper, we use Heat Kernel Signature (HKS) as the local features to represent non-rigid 3D models and further propose the retrieval method based on scale-invariant local features. Firstly, we extract key-points at multiple scales automatically. Then, the HKS local features are computed for each key-point. However, the HKS features are sensitive to scale. In order to solve this problem, we convert the scale problem into the translation problem using the diffusion Wavelets transform. To solve the translation problem, we use a kind of histogram equalization technique. Finally, we use the bipartite graph matching algorithm to compute similarity between the 3D models. Experimental results on two public benchmarks show that our method outperforms state-of-the-art methods for non-rigid 3D models retrieval.

show abstract

Retrieval of non-rigid 3D shapes from multiple aspects

Cited by 18 publications

References 26 publications

FOSIR: Fuzzy-Object-Shape for Image Retrieval applications

FOSIR: Fuzzy-Object-Shape for Image Retrieval applications

Revisit Point Cloud Recognition From the Viewpoint of Data Mixture

A non-rigid 3D model retrieval method based on scale-invariant heat kernel signature features

Contact Info

Product

Resources

About