A survey of content based 3D shape retrieval methods

Tangelder, Johan W. H.; Veltkamp, Remco C.

doi:10.1109/smi.2004.1314502

Cited by 492 publications

(468 citation statements)

References 67 publications

Supporting

Mentioning

464

Contrasting

Unclassified

Order By: Relevance

“…Below we briefly review the representative approaches in each category. Detailed survey papers of shape retrial methods can be found in [1] [16].…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In the past two decades, extensive efforts have been made to design effective 3D shape retrieval algorithms [1]. The existing work is mainly focused on two search scenarios, i.e., search by sketch [2][3] (Figure 1(a)) and search with CAD models as query input [1] (Figure 1(b)). Along with the advances of low-cost depth sensors such as Microsoft Kinect, PrimeSense sensors, and the newly revealed mobile depth sensor from Google [4], there is tremendous growth of user-generated 3D data, which promotes the study of a new cross-domain retrieval problem, i.e., search with user-captured models, where the users capture potentially noisy depth data and images of the object to their interest, and then use reconstructed 3D models as queries to find similar 3D shapes from a large collection of high-quality CAD models as illustrated in Figure 1(c).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. The recent advances of low-cost and mobile depth sensors dramatically extend the potential of 3D shape retrieval and analysis. While the traditional research of 3D retrieval mainly focused on searching by a rough 2D sketch or with a high-quality CAD model, we tackle a novel and challenging problem of cross-domain 3D shape retrieval, in which users can use 3D scans from low-cost depth sensors like Kinect as queries to search CAD models in the database. To cope with the imperfection of user-captured models such as model noise and occlusion, we propose a cross-domain shape retrieval framework, which minimizes the potential function of a Conditional Random Field to efficiently generate the retrieval scores. In particular, the potential function consists of two critical components: one unary potential term provides robust crossdomain partial matching and the other pairwise potential term embeds spatial structures to alleviate the instability from model noise. Both potential components are efficiently estimated using random forests with 3D local features, forming a Regression Tree Field framework. We conduct extensive experiments on two recently released user-captured 3D shape datasets and compare with several state-of-the-art approaches on the cross-domain shape retrieval task. The experimental results demonstrate that our proposed method outperforms the competing methods with a significant performance gain.

show abstract

“…Below we briefly review the representative approaches in each category. Detailed survey papers of shape retrial methods can be found in [1] [16].…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…Interpreting and comparing shapes are challenging issues in computer vision, computer graphics and pattern recognition [11,12]. Topological Persistenceincluding Persistent Homology [9] and Size Theory [1,10] -has proven to be a successful comparison/retrieval/classification (hereafter CRC) scheme.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale Approximation of the Matching Distance for Shape Retrieval

Cerri

Fabio

Medri

2012

Computational Topology in Image Context

View full text Add to dashboard Cite

Abstract. This paper deals with the concepts of persistence diagrams and matching distance. They are two of the main ingredients of Topological Persistence, which has proven to be a promising framework for shape comparison. Persistence diagrams are descriptors providing a signature of the shapes under study, while the matching distance is a metric to compare them. One drawback in the application of these tools is the computational costs for the evaluation of the matching distance. The aim of the present paper is to introduce a new framework for the approximation of the matching distance, which does not affect the reliability of the entire approach in comparing shapes, and extremely reduces computational costs. This is shown through experiments on 3D-models.

show abstract

“…The World Wide Web allows to incorporate 3D models in sites and home pages. As a consequence of this trend, there is a strong interest in methods for recognition and retrieval of 3D objects [1,2]. Object recognition (matching) may be very time consuming because of all variations that may occur: different position (object origin), rotation, size and also mesh resolution.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Retrieval of 3D Polygonal Objects Based on Multiresolution Signatures

Lam

Buf

2011

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. In this paper we present a method for retrieving 3D polygonal objects by using two sets of multiresolution signatures. Both sets are based on the progressive elimination of object's details by iterative processing of the 3D meshes. The first set, with five parameters, is based on mesh smoothing. This mainly affects an object's surface. The second set, with three parameters, is based on difference volumes after successive mesh erosions and dilations. Characteristic feature vectors are constructed by combining the features at three mesh resolutions of each object. In addition to being invariant to mesh resolution, the feature vectors are invariant to translation, rotation and size of the objects. The method was tested on a set of 40 complex objects with mesh resolutions different from those used in constructing the feature vectors. By using all eight features, the average ranking rate obtained was 1.075: 37 objects were ranked first and only 3 objects were ranked second. Additional tests were carried out to determine the significance of individual features and all combinations. The same ranking rate of 1.075 can be obtained by using some combinations of only three features.

show abstract

A survey of content based 3D shape retrieval methods

Abstract: Abstract

Cited by 492 publications

References 67 publications

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Multi-scale Approximation of the Matching Distance for Shape Retrieval

Retrieval of 3D Polygonal Objects Based on Multiresolution Signatures

Contact Info

Product

Resources

About