Filters








89,060 Hits in 4.3 sec

Retrieving 3D shapes based on their appearance

Ryutarou Ohbuchi, Masatoshi Nakazawa, Tsuyoshi Takei
2003 Proceedings of the 5th ACM SIGMM international workshop on Multimedia information retrieval - MIR '03  
One of the issues in comparing 3D shapes is the diversity of shape representations used to represent these "3D" shapes.  ...  In this paper, we propose an algorithm for shape-similarity comparison and retrieval of 3D shapes defined as polygon soup.  ...  Shigeo Takahashi and anonymous reviewers for their valuable comments.  ... 
doi:10.1145/973264.973272 dblp:conf/mir/OhbuchiNT03 fatcat:rqxpfu5vaben7ntipxd73c2oza

Joint embeddings of shapes and images via CNN image purification

Yangyan Li, Hao Su, Charles Ruizhongtai Qi, Noa Fish, Daniel Cohen-Or, Leonidas J. Guibas
2015 ACM Transactions on Graphics  
Our joint embedding allows cross-view image retrieval, image-based shape retrieval, as well as shape-based image retrieval.  ...  We construct the embedding space using 3D shape similarity measure, as 3D shapes are more pure and complete than their appearance in images, leading to more robust distance metrics.  ...  We evaluate the image-based shape retrieval performance by the top-k instance retrieval accuracy on the benchmark.  ... 
doi:10.1145/2816795.2818071 fatcat:4dt5y2olf5eodpykwuckhutuse

Pose Insensitive 3D Retrieval by Poisson Shape Histogram [chapter]

Pan Xiang, Chen Qi Hua, Fang Xin Gang, Zheng Bo Chuan
2007 Lecture Notes in Computer Science  
With the rapid increase of available 3D models, content-based 3D retrieval is attracting more and more research interests. Histogram is the most widely in constructing 3d shape descriptor.  ...  Retrieving experiments for the shape benchmark database have proven that poisson shape histogram can achieve better performance than other similar histogram-based shape representations.  ...  This section mainly gives a brief review on statistical shape description for content-based 3D retrieval.  ... 
doi:10.1007/978-3-540-72586-2_4 fatcat:axqjsfikgbawropxfr4cbzzbqe

Preface to Special Issue on 3DOR 2011

Alfredo Ferreira, Hamid Laga, Tobias Schreck, Remco Veltkamp
2012 The Visual Computer  
Sfikas et al. propose non-rigid 3D object retrieval based on conformal geometry analysis in conjunction with a tree-based representation and a custom matching function.  ...  shape retrieval.  ... 
doi:10.1007/s00371-012-0747-3 fatcat:h43a7wa6gjavbfzlrfpd6paza4

Spatially Enhanced Bags of Words for 3D Shape Retrieval [chapter]

Xiaolan Li, Afzal Godil, Asim Wagan
2008 Lecture Notes in Computer Science  
This paper presents a new method for 3D shape retrieval based on the bags-of-words model along with a weak spatial constraint.  ...  The spatial constraint shows improved performance on 3D shape retrieval tasks.  ...  Accordingly, a retrieval rank list is obtained based on it. Experiments Princeton Shape Benchmark (PSB) [Shilane04] is chosen as the 3D shape database.  ... 
doi:10.1007/978-3-540-89639-5_34 fatcat:vcpibqf7hbeztndl34ccynbgtu

Content-Based 3D Model Retrieval for Digital Museum [chapter]

Jie Tang, Fuyan Zhang
2006 Lecture Notes in Computer Science  
Experiments showed that, our method achieved better performance improvement especially for appearance retrieval of 3d model.  ...  In this paper, we propose a new shape feature for shapesimilarity search of 3D polygonal-mesh models in digital museum. The shape feature is an extension of the D2 shape functions proposed by Osada.  ...  It is thus necessary to have a content-based search and retrieval systems for 3D models that are based on the features intrinsic to the 3D models.  ... 
doi:10.1007/11736639_171 fatcat:wkvmcpatd5edto52xltnifxxoi

Foreword to the C&G Special Section on 3D Object Retrieval (3DOR2018)

Alexandru Telea, Theoharis Theoharis
2019 Computers & graphics  
Their sustained efforts have been crucial for getting this high-quality Special Section assembled. We also thank the C&G staff including the editor-in-chief Prof.  ...  The papers cover a wide range of topics including mixed-modality retrieval, retrieval based on partial local shape information, and the usage of machine learning techniques to support shape retrieval.  ...  Finally, Thompson and Biasotti [4] extend the tasks of texture image retrieval and classification to their application on decorations and textures on 3D surfaces.  ... 
doi:10.1016/j.cag.2019.01.005 fatcat:xegg3lewhva43m5jh54mqc7nvq

Non-rigid 3D shape retrieval using Multidimensional Scaling and Bag-of-Features

Zhouhui Lian, Afzal Godil, Xianfang Sun, Hai Zhang
2010 2010 IEEE International Conference on Image Processing  
Matching non-rigid shapes is a challenging research field in content-based 3D object retrieval. In this paper, we present an image-based method to effectively address this problem.  ...  Index Terms-3D shape retrieval, Non-rigid 3D shape, Multidimensional Scaling (MDS), Bag-of-Features (BOF)  ...  INTRODUCTION The explosion in the number of 3D models has led to the rapid development of 3D shape retrieval systems that, given a query object, retrieve similar 3D models based on their shapes.  ... 
doi:10.1109/icip.2010.5654226 dblp:conf/icip/LianGSZ10 fatcat:jffbfcq3dnfbxax4vzfahelbpy

SHREC'10 Track: Non-rigid 3D Shape Retrieval [article]

Z. Lian, A. Godil, T. Fabry, T. Furuya, J. Hermans, R. Ohbuchi, C. Shu, D. Smeets, P. Suetens, D. Vandermeulen, S. Wuhrer
2010 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Non-rigid shape matching is one of the most challenging fields in content-based 3D object retrieval.  ...  The aim of the 3D Shape Retrieval Contest 2010 (SHREC'10) track on non-rigid 3D shape retrieval is to evaluate and compare the effectiveness of different methods run on a non-rigid 3D shape benchmark consisting  ...  We would like to thank the Shape Analysis Group in McGill University for providing the McGill 3D Shape Benchmark database, and we are also grateful to Benny Cheung for creating the web interface mentioned  ... 
doi:10.2312/3dor/3dor10/101-108 fatcat:mu62iibph5cojanbonil6vvvh4

Multi Voxel Descriptor for 3D Texture Retrieval

Hero Yudo Martono
2016 Emitter: International Journal of Engineering Technology  
In this paper, we present a new feature descriptors which exploit voxels for 3D textured retrieval system when models vary either by geometric shape or texture or both.  ...  First, we perform pose normalisation to modify arbitrary 3D models in order to have same orientation. We then map the structure of 3D models into voxels.  ...  We generate some features to retrieve 3D models based on shape, color and texture.  ... 
doi:10.24003/emitter.v4i1.110 fatcat:wwsl6ip3sbhx5odc75qfia6n3a

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Hang Su, Subhransu Maji, Evangelos Kalogerakis, Erik Learned-Miller
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
A longstanding question in computer vision concerns the representation of 3D shapes for recognition: should 3D shapes be represented with descriptors operating on their native 3D formats, such as voxel  ...  We address this question in the context of learning to recognize 3D shapes from a collection of their rendered views on 2D images.  ...  Acknowledgements We thank Yanjie Li for her help on rendering meshes. We thank NVIDIA for their generous donation of GPUs used in this research. Our work was partially supported by NSF (CHS-1422441).  ... 
doi:10.1109/iccv.2015.114 dblp:conf/iccv/SuMKL15 fatcat:4gyiniflprhj3pxu466yild5ku

Salient local visual features for shape-based 3D model retrieval

Ryutarou Ohbuchi, Kunio Osada, Takahiko Furuya, Tomohisa Banno
2008 2008 IEEE International Conference on Shape Modeling and Applications  
In this paper, we describe a shape-based 3D model retrieval method based on multi-scale local visual features.  ...  3D shape retrieval methods.  ...  The authors also would like to thank those who created benchmark databases and those who made available codes for their shape features.  ... 
doi:10.1109/smi.2008.4547955 dblp:conf/smi/OhbuchiOFB08 fatcat:67sfzxco4ngobbp2x4v4jtma24

Deep point-to-subspace metric learning for sketch-based 3D shape retrieval

Yinjie Lei, Ziqin Zhou, Pingping Zhang, Yulan Guo, Zijun Ma, Lingqiao Liu
2019 Pattern Recognition  
One key issue in managing a large scale 3D shape dataset is to identify an effective way to retrieve a shape-of-interest.  ...  Matching between them is a cross-modality retrieval problem, and the state-of-the-art solution is to project the sketch and the 3D shape into a common space with which the cross-modality similarity can  ...  Traditional sketch-based 3D shape retrieval 75 3D shape.  ... 
doi:10.1016/j.patcog.2019.106981 fatcat:kp4rqfodmbbtxcomm3rykhii6y

A New Shape Benchmark for 3D Object Retrieval [chapter]

Rui Fang, Afzal Godil, Xiaolan Li, Asim Wagan
2008 Lecture Notes in Computer Science  
Recently, content based 3D shape retrieval has been an active area of research. Benchmarking allows researchers to evaluate the quality of results of different 3D shape retrieval approaches.  ...  Here, we propose a new publicly available 3D shape benchmark to advance the state of art in 3D shape retrieval.  ...  With a number of shape based retrieval methods appearing in the current literature, the question now is how to evaluate shape retrieval algorithms rationally with high confidence.  ... 
doi:10.1007/978-3-540-89639-5_37 fatcat:hrwng5dhgzctvohnpaeflloxze

Comparison of Dimension Reduction Methods for Database-Adaptive 3D Model Retrieval [chapter]

Ryutarou Ohbuchi, Jun Kobayashi, Akihiro Yamamoto, Toshiya Shimizu
2008 Lecture Notes in Computer Science  
We experimentally compare six such dimension reduction algorithms, both linear and non-linear, for their efficacy in the context of shape-based 3D model retrieval.  ...  Distance measures, along with shape features, are the most critical components in a shape-based 3D model retrieval system.  ...  Acknowledgements The authors would like to thank those who created benchmark databases, those who made available codes for their shape features, and those who made available codes for various learning  ... 
doi:10.1007/978-3-540-79860-6_16 fatcat:lo5bcpw25nc77gegimjwdy7eja
« Previous Showing results 1 — 15 out of 89,060 results