3DOR: Eurographics Workshop on 3D Object Retrieval

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/307

Browse

Now showing 1 - 20 of 221

3D Object Retrieval using an Efficient and Compact Hybrid Shape Descriptor
(The Eurographics Association, 2008) Papadakis, Panagiotis; Pratikakis, Ioannis; Theoharis, Theoharis; Passalis, Georgios; Perantonis, Stavros; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
Abstract We present a novel 3D object retrieval method that relies upon a hybrid descriptor which is composed of 2D features based on depth buffers and 3D features based on spherical harmonics. To compensate for rotation, two alignment methods, namely CPCA and NPCA, are used while compactness is supported via scalar feature quantization to a set of values that is further compressed using Huffman coding. The superior performance of the proposed retrieval methodology is demonstrated through an extensive comparison against state-of-the-art methods on standard datasets.
On-line and Open Platform for 3D Object Retrieval
(The Eurographics Association, 2008) Bonhomme, Benoit Le; Mustafa, B.; Celakovsky, Sasko; Preda, Marius; Preteux, Francoise; Davcev, D.; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
In this paper we present the MyMultimediaWorld Internet-based platform designed to benchmark descriptors and description scheme for 3D object retrieval purpose. Relying on the MPEG-4 and MPEG-7 multimedia standards for data representation and description respectively, this open platform is designed to host multiple datasets, descriptors, descriptor extraction algorithms and similarity measures. We implemented an easy-to-use API designed to make the integration of the 3D object retrieval technology of third-party researchers agnostic to and independent of the global system complexity. Benchmarking results are automatically updated accordingly and presented qualitatively by displaying the 3D retrieved objects and quantitatively by providing the estimates of the state-of-the art performance criteria.
A Neurofuzzy Approach to Active Learning based Annotation Propagation for 3D Object Databases
(The Eurographics Association, 2008) Lazaridis, Michalis; Daras, Petros; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
Most existing Content-based Information Retrieval (CBIR) systems using semantic annotation, either annotate all the objects in a database (full annotation) or a manually selected subset (partial annotation) in order to increase the system's performance. As databases become larger, the manual effort needed for full annotation becomes unaffordable. In this paper, a fully automatic framework for partial annotation and annotation propagation, applied to 3D content, is presented. A part of the available 3D objects is automatically selected for manually annotation, based on their 'information content'. For the non-annotated objects, the annotation is automatically propagated using a neurofuzzy model, which is trained during the manual annotation process and takes into account the information hidden into the already annotated objects. Experimental results show that the proposed method is effective, fast and robust to outliers. The framework can be seen as another step towards bridging the semantic gap between low-level geometric characteristics (content) and intuitive semantics (context).
Face Recognition by SVMs Classification and Manifold Learning of 2D and 3D Radial Geodesic Distances
(The Eurographics Association, 2008) Berretti, Stefano; Bimbo, Alberto Del; Pala, Pietro; Mata, Francisco Josè Silva; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
An original face recognition approach based on 2D and 3D Radial Geodesic Distances (RGDs), respectively computed on 2D face images and 3D face models, is proposed in this work. In 3D, the RGD of a generic point of a 3D face surface is computed as the length of the particular geodesic that connects the point with a reference point along a radial direction. In 2D, the RGD of a face image pixel with respect to a reference pixel accounts for the difference of gray level intensities of the two pixels and the Euclidean distance between them. Support Vector Machines (SVMs) are used to perform face recognition using 2D- and 3D-RGDs. Due to the high dimensionality of face representations based on RGDs, embedding into lower-dimensional spaces using manifold learning is applied before SVMs classification. Experimental results are reported for 3D-3D and 2D-3D face recognition using the proposed approach.
Isometry-invariant Matching of Point Set Surfaces
(The Eurographics Association, 2008) Ruggeri, Mauro R.; Saupe, Dietmar; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
Shape deformations preserving the intrinsic properties of a surface are called isometries. An isometry deforms a surface without tearing or stretching it, and preserves geodesic distances. We present a technique for matching point set surfaces, which is invariant with respect to isometries. A set of reference points, evenly distributed on the point set surface, is sampled by farthest point sampling. The geodesic distance between reference points is normalized and stored in a geodesic distance matrix. Each row of the matrix yields a histogram of its elements. The set of histograms of the rows of a distance matrix is taken as a descriptor of the shape of the surface. The dissimilarity between two point set surfaces is computed by matching the corresponding sets of histograms with bipartite graph matching. This is an effective method for classifying and recognizing objects deformed with isometric transformations, e.g., non-rigid and articulated objects in different postures.
Part Analogies in Sets of Objects
(The Eurographics Association, 2008) Shalom, Shy; Shapira, Lior; Shamir, Ariel; Cohen-Or, Daniel; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
Shape retrieval can benefit from analogies among similar shapes and parts of different objects. By partitioning an object to meaningful parts and finding analogous parts in other objects, sub-parts and partial match queries can be utilized. First by searching for similar parts in the context of their shape, and second by finding similarities even among objects that differ in their general shape and topology. Moreover, analogies can create the basis for semantic text-based searches: for instance, in this paper we demonstrate a simple annotation tool that carries tags of object parts from one model to many others using analogies. We partition 3D objects based on the shape-diameter function (SDF), and use it to find corresponding parts in other objects. We present results on finding analogies among numerous objects from shape repositories, and demonstrate sub-part queries using an implementation of a simple search and retrieval application.
Similarity Score Fusion by Ranking Risk Minimization for 3D Object Retrieval
(The Eurographics Association, 2008) Akgül, Ceyhun Burak; Sankur, Bülent; Yemez, Yücel; Schmitt, Francis; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
In this work, we introduce a score fusion scheme to improve the 3D object retrieval performance. The state of the art in 3D object retrieval shows that no single descriptor is capable of providing fine grain discrimination required by prospective 3D search engines. The proposed fusion algorithm linearly combines similarity information originating from multiple shape descriptors and learns their optimal combination of weights by minimizing the empirical ranking risk criterion. The algorithm is based on the statistical ranking framework [CLV07], for which consistency and fast rate of convergence of empirical ranking risk minimizers have been established. We report the results of ontology-driven and relevance feedback searches on a large 3D object database, the Princeton Shape Benchmark. Experiments show that, under query formulations with user intervention, the proposed score fusion scheme boosts the performance of the 3D retrieval machine significantly.
A 3D Face Recognition Algorithm Using Histogram-based Features
(The Eurographics Association, 2008) Zhou, Xuebing; Seibert, Helmut; Busch, Christoph; Funk, Wolfgang; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
We present an automatic face recognition approach, which relies on the analysis of the three-dimensional facial surface. The proposed approach consists of two basic steps, namely a precise fully automatic normalization stage followed by a histogram-based feature extraction algorithm. During normalization the tip and the root of the nose are detected and the symmetry axis of the face is determined using a PCA analysis and curvature calculations. Subsequently, the face is realigned in a coordinate system derived from the nose tip and the symmetry axis, resulting in a normalized 3D model. The actual region of the face to be analyzed is determined using a simple statistical method. This area is split into disjoint horizontal subareas and the distribution of depth values in each subarea is exploited to characterize the face surface of an individual. Our analysis of the depth value distribution is based on a straightforward histogram analysis of each subarea. When comparing the feature vectors resulting from the histogram analysis we apply three different similarity metrics. The proposed algorithm has been tested with the FRGC v2 database, which consists of 4950 range images. Our results indicate that the city block metric provides the best classification results with our feature vectors. The recognition system achieved an equal error rate of 5.89% with correctly normalized face models.
Characterizing Shape Using Conformal Factors
(The Eurographics Association, 2008) Ben-Chen, Mirela; Gotsman, Craig; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
We present a new 3D shape descriptor based on conformal geometry. Our descriptor is invariant under non-rigid quasi-isometric transformations, such as pose changes of articulated models, and is both compact and efficient to compute. We demonstrate the performance of our descriptor on a database of watertight models, and show it is comparable with state-of-the-art descriptors.
Markov Random Fields for Improving 3D Mesh Analysis and Segmentation
(The Eurographics Association, 2008) Lavoué, Guillaume; Wolf, Christian; Stavros Perantonis and Nikolaos Sapidis and Michela Spagnuolo and Daniel Thalmann
Mesh analysis and clustering have became important issues in order to improve the efficiency of common processing operations like compression, watermarking or simplification. In this context we present a new method for clustering / labeling a 3D mesh given any field of scalar values associated with its vertices (curvature, density, roughness etc.). Our algorithm is based on Markov Random Fields, graphical probabilistic models. This Bayesian framework allows (1) to integrate both the attributes and the geometry in the clustering, and (2) to obtain an optimal global solution using only local interactions, due to the Markov property of the random field. We have defined new observation and prior models for 3D meshes, adapted from image processing which achieve very good results in terms of spatial coherency of the labeling. All model parameters are estimated, resulting in a fully automatic process (the only required parameter is the number of clusters) which works in reasonable time (several seconds).
Retrieval of 3D Articulated Objects Using a Graph-based Representation
(The Eurographics Association, 2009) Agathos, Alexander; Pratikakis, Ioannis; Papadakis, Panagiotis; Perantonis, Stavros; Azariadis, Philip; Sapidis, Nickolas S.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
Most of the approaches which address the problem of 3D object retrieval, use global descriptors of the objects which fail to consistently compensate for the intra-class variability of articulated objects. In this paper, a retrieval methodology is presented which is based upon a graph-based object representation. This is composed of a meaningful new mesh segmentation along with a graph matching between the graph of the query object and each of the graphs that correspond to the objects of the 3D object database. The graph matching algorithm is based on the Earth Mover's Distance (EMD) similarity measure which is calculated using a new ground distance assignment. The superior performance of the proposed methodology is shown after an extensive experimentation comprising alternative descriptors for the constituent components of the 3D object as well as comparison with state of the art retrieval algorithms.
SHREC'09 Track: Structural Shape Retrieval on Watertight Models
(The Eurographics Association, 2009) Hartveldt, J.; Spagnuolo, M.; Axenopoulos, A.; Biasotti, S.; Daras, P.; Dutagaci, H.; Furuya, T.; Godil, A.; Li, X.; Mademlis, A.; Marini, S.; Napoleon, T.; Ohbuchi, R.; Tezuka, M.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
The annual SHape REtrieval Contest (SHREC) measures the performance of 3D model retrieval methods for several different types of models and retrieval purposes. In this contest the structural shape retrieval track focuses on the retrieval of 3d models which exhibit a relevant similarity in the shape structure. Shape structure is typically characterised by features like protrusions, holes and concavities. It defines relationships in which components of the shape are connected.
Visual Vocabulary Signature for 3D Object Retrieval and Partial Matching
(The Eurographics Association, 2009) Toldo, Roberto; Castellani, Umberto; Fusiello, Andrea; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
In this paper a novel object signature is proposed for 3D object retrieval and partial matching. A part-based representation is obtained by partitioning the objects into subparts and by characterizing each segment with different geometric descriptors. Therefore, a Bag ofWords framework is introduced by clustering properly such descriptors in order to define the so called 3D visual vocabulary. In this fashion, the object signature is defined as a histogram of 3D visual word occurrences. Several examples on the Aim@Shape watertight dataset demonstrate the versatility of the proposed method in matching either 3D objects with articulated shape changes or partially occluded or compound objects. In particular, a comparison with the methods that participated to the Shape Retrieval contest 2007 (SHREC) reports satisfactory results for both object retrieval and partial matching.
A 3D Shape Benchmark for Retrieval and Automatic Classification of Architectural Data
(The Eurographics Association, 2009) Wessel, Raoul; Blümel, Ina; Klein, Reinhard; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
When drafting new buildings, architects make intensive use of existing 3D models including building elements, furnishing, and environment elements. These models are either directly included into the draft or serve as a source for inspiration. To allow efficient reuse of existing 3D models, shape retrieval methods considering the specific requirements of architects must be developed. Unfortunately, common 3D shape benchmarks which are used to evaluate the performance of retrieval algorithms are not well suited for architectural data. First, they incorporate models which are not related to this domain, and second and even more important, the provided classification schemes usually do not match an architect's intuition regarding their notion of design and function. To overcome these drawbacks, we present a freely downloadable shape benchmark especially designed for architectural 3D models. It currently contains 2257 objects from various content providers, including companies specialized on 3D CAD applications. All models are classified according to a scheme developed in close cooperation with architects taking into account their specific requirements regarding design and function. Additionally, we show retrieval results for this benchmark using unsupervised and supervised shape retrieval methods and discuss the specific problems regarding retrieval of architectural 3D models.
Partial Matching for Real Textured 3D Objects using Color Cubic Higher-order Local Auto-Correlation Features
(The Eurographics Association, 2009) Kanezaki, Asako; Harada, T.; Kuniyoshi, Y.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
In recent years the need for the retrieval of real 3D objects is growing more and more. However, if the 3D models are obtained without the use of special equipment such as engineered environments or multi-camera systems, they are often incomplete, making retrieval difficult. On the other hand, real models often include rich texture information, which can compensate for the limited shape information. In this paper we present new 3D shape features which take into account an object's texture. We demonstrate the retrieval performance of these features on a dataset of real textured objects and a real color 3D scene.
SkelTre - Fast Skeletonisation for Imperfect Point Cloud Data of Botanic Trees
(The Eurographics Association, 2009) Bucksch, Alexander; Lindenbergh, Roderik C.; Menenti, M.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
Terrestrial laser scanners capture 3D geometry as a point cloud. This paper reports on a new algorithm aiming at the skeletonisation of a laser scanner point cloud, representing a botanical tree without leafs. The resulting skeleton can subsequently be applied to obtain tree parameters like length and diameter of branches for botanic applications. Scanner-produced point cloud data are not only subject to noise, but also to undersampling and varying point densities, making it challenging to extract a topologically correct skeleton. The skeletonisation algorithm proposed in this paper consists of three steps: (i) extraction of a graph from an octree organization, (ii) reduction of the graph to the skeleton and (iii) embedding of the skeleton into the point cloud. The results are validated on laser scanner point clouds representing botanic trees. On a reference tree, the mean and maximal distance of the point cloud points to the skeleton could be reduced from 1.8 to 1.5 cm for the mean and from 15.6 to 10.5 cm for the maximum, compared to results from a previously developed method.
SHREC'09 Track: Generic Shape Retrieval
(The Eurographics Association, 2009) Godil, A.; Dutagaci, H.; Akgül, C.; Axenopoulos, A.; Bustos, B.; Chaouch, M.; Daras, P.; Furuya, T.; Kreft, S.; Lian, Z.; Napoléon, T.; Mademlis, A.; Ohbuchi, R.; Rosin, P. L.; Sankur, B.; Schreck, Tobias; Sun, X.; Tezuka, M.; Verroust-Blondet, A.; Walter, M.; Yemez, Y.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
In this paper we present the results of the SHREC'09- Generic Shape Retrieval Contest. The aim of this track was to evaluate the performances of various 3D shape retrieval algorithms on the NIST generic shape benchmark. We hope that the NIST shape benchmark will provide valuable contributions to the 3D shape retrieval community. Seven groups have participated in the track and they have submitted 22 sets of rank lists based on different methods and parameters. The performance evaluation of the SHREC'09- Generic Shape Retrieval Contest is based on 6 different metrics.
Multilevel Relevance Feedback for 3D Shape Retrieval
(The Eurographics Association, 2009) Giorgi, Daniela; Frosini, Patrizio; Spagnuolo, Michela; Falcidieno, Bianca; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
Relevance feedback techniques are expected to play an important role in 3D search engines, as they help to bridge the semantic gap between the user and the system: similarity is a cognitive process, depending on the observer. We propose a novel relevance feedback technique, whose basic idea is threefold. First of all, the user is provided with a variety of shape descriptors, analysing different shape properties. The user then expresses her similarity concept through a friendly interface which supports multilevel relevance judgements. Finally, the system inhibits the role of the shape properties that do not reflect the user's idea of similarity. The assumption is that similarity may emerge as an inhibition of differences, i.e., as a lack of diversity with respect to the shape properties taken into account. The proposed technique is based on a simple scaling procedure, which does not require any a priori learning or optimization of parameters.
Template Based Shape Descriptor
(The Eurographics Association, 2009) Rustamov, Raif M.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
We introduce a new 3D shape descriptor which maps the surface features onto an arbitrary template surface using mean-value interpolation. A compact numerical shape descriptor is extracted using manifold harmonics on the template. We show that mean-value interpolation is a strong alternative to the often used projection. The utility of using different templates is established by showing that concatenating descriptors coming from different templates improves retrieval quality.
SHREC'09 Track: Querying with Partial Models
(The Eurographics Association, 2009) Dutagaci, H.; Godil, A.; Axenopoulos, A.; Daras, P.; Furuya, T.; Ohbuchi, R.; Michela Spagnuolo and Ioannis Pratikakis and Remco Veltkamp and Theoharis Theoharis
The objective of the SHREC'09 Querying with Partial Models is to compare the performances of algorithms that accept a range image as the query and retrieve relevant 3D models from a database. The use of a range scan as the query addresses a real life scenario where the task of the system is to analyze a 3D scene and to identify what type of objects are present in the scene. Another benefit of developing retrieval algorithms based on range inputs is that they enable a simple 3D search interface composed of a desktop 3D scanner. Two groups have participated in the contest and have provided rank lists for the query set that is composed of range scans of 20 objects. This paper presents descriptions of the participants' methods and the results of the contest.

Browse

Browsing 3DOR: Eurographics Workshop on 3D Object Retrieval by Issue Date

Results Per Page

Sort Options