3DOR: Eurographics Workshop on 3D Object Retrieval

Permanent URI for this community

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

Browse

Now showing 1 - 9 of 9

Automatic Location of Landmarks used in Manual Anthropometry
(The Eurographics Association, 2014) Giachetti, A.; Mazzi, E.; Piscitelli, F.; Aono, M.; Hamza, A. Ben; Bonis, T.; Claes, P.; Godil, A.; Li, C.; Ovsjanikov, M.; Patraucean, V.; Shu, C.; Snyders, J.; Suetens, P.; Tatsuma, A.; Vandermeulen, D.; Wuhrer, S.; Xi, P.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
In this paper we report the results of the SHREC 2014 track on automatic location of landmarks used in manual anthropometry. The track has been organized to test the ability of modern computational geometry/pattern recognition techniques to locate accurately reference points used for tape based measurement. Participants had to locate six specific landmarks on human models acquired with a structured light body scanner. A training set of 50 models with manual annotations of the corresponding landmarks location was provided to train the algorithms. A test set of 50 different models was also provided, without annotations. Accuracy of the automatic location methods was tested via computing geodesic distances of the detected points from manually placed ones and evaluating different quality scores and functions.
Compact Vectors of Locally Aggregated Tensors for 3D Shape Retrieval
(The Eurographics Association, 2013) Tabia, Hedi; Picard, David; Laga, Hamid; Gosselin, Philippe-Henri; Umberto Castellani and Tobias Schreck and Silvia Biasotti and Ioannis Pratikakis and Afzal Godil and Remco Veltkamp
During the last decade, a significant attention has been paid, by the computer vision and the computer graphics communities, to three dimensional (3D) object retrieval. Shape retrieval methods can be divided into three main steps: the shape descriptors extraction, the shape signatures and their associated similarity measures, and the machine learning relevance functions. While the first and the last points have vastly been addressed in recent years, in this paper, we focus on the second point; presenting a new 3D object retrieval method using a new coding/pooling technique and powerful 3D shape descriptors extracted from 2D views. For a given 3D shape, the approach extracts a very large and dense set of local descriptors. From these descriptors, we build a new shape signature by aggregating tensor products of visual descriptors. The similarity between 3D models can then be efficiently computed with a simple dot product. We further improve the compactness and discrimination power of the descriptor using local Principal Component Analysis on each cluster of descriptors. Experiments on the SHREC 2012 and the McGill benchmarks show that our approach outperforms the state-of-the-art techniques, including other BoF methods, both in compactness of the representation and in the retrieval performance.
Fisher Encoding of Adaptive Fast Persistent Feature Histograms for Partial Retrieval of 3D Pottery Objects
(The Eurographics Association, 2014) Savelonas, Michalis A.; Pratikakis, Ioannis; Sfikas, Konstantinos; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Cultural heritage is a natural application domain for partial 3D object retrieval, since it usually involves objects that have only been partially preserved. This work introduces a method for the retrieval of 3D pottery objects, based on partial point cloud queries. The proposed method extracts fast persistent feature histograms calculated adaptively to the mean point distances of the point cloud query. The extracted set of vectors is refined by a denoising component, which employs statistical filtering. The remaining vectors are further refined by a filtering component, which discards points surrounded by surfaces of extremely fine-grained irregularity, often associated with artefact damages. A bag of visual words scheme is used, which starts from the final set of persistent feature histogram vectors and estimates Gaussian mixture models by means of an expectation maximization algorithm. The resulting Gaussian mixture models define the visual codebook, which is used within the context of Fisher encoding. Experiments are performed on a challenging dataset of pottery objects, obtained from the publicly available Hampson collection.
Geometric Histograms of 3D Keypoints for Face Identification with Missing Parts
(The Eurographics Association, 2013) Berretti, Stefano; Werghi, Naoufel; Bimbo, Alberto del; Pala, Pietro; Umberto Castellani and Tobias Schreck and Silvia Biasotti and Ioannis Pratikakis and Afzal Godil and Remco Veltkamp
In this work, an original solution to 3D face identification is proposed, which supports recognition also in the case of probes with missing parts. Distinguishing traits of the face are captured by first extracting 3D keypoints of a face scan, then measuring how the face surface changes in the keypoints neighborhood using a local descriptor. To this end, an adaptation of the meshDOG algorithm to the case of 3D faces is proposed, together with a multi-ring geometric histogram descriptor. Face similarity is then evaluated by comparing local keypoint descriptors across inlier pairs of matching keypoints between probe and gallery scans. Experiments have been performed to assess the keypoints distribution and repeatability. Recognition accuracy of the proposed approach has been evaluated on the Bosphorus database, showing competitive results with respect to existing 3D face biometrics solutions.
GeoTopo: Dynamic 3D Facial Expression Retrieval Using Topological and Geometric Information
(The Eurographics Association, 2014) Danelakis, Antonios; Theoharis, Theoharis; Pratikakis, Ioannis; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Recently, a lot of research has been dedicated to address the problem of facial expression recognition in dynamic sequences of 3D face scans. On the contrary, no research has been conducted on facial expression retrieval using dynamic 3D face scans. This paper illustrates the first results on the area of dynamic 3D facial expression retrieval. To this end, a novel descriptor is created, namely GeoTopo, capturing the topological as well as the geometric information of the 3D face scans along time. Experiments have been implemented using the angry, happy and surprise expressions of the publicly available dataset BU - 4DFE. The obtained retrieval results are very promising. Furthermore, a methodology which exploits the retrieval results, in order to achieve unsupervised dynamic 3D facial expression recognition, is presented. The aforementioned unsupervised methodology achieves classification accuracy comparable to the supervised dynamic 3D facial expression recognition state-of-the-art techniques.
Partial 3D Object Retrieval combining Local Shape Descriptors with Global Fisher Vectors
(The Eurographics Association, 2015) Savelonas, Michalis A.; Pratikakis, Ioannis; Sfikas, Konstantinos; I. Pratikakis and M. Spagnuolo and T. Theoharis and L. Van Gool and R. Veltkamp
This work introduces a partial 3D object retrieval method, applicable on both meshes and point clouds, which is based on a hybrid shape matching scheme combining local shape descriptors with global Fisher vectors. The differential fast point feature histogram (dFPFH) is defined so as to extend the well-known FPFH descriptor in order to capture local geometry transitions. Local shape similarity is quantified by averaging the minimum weighted distances associated with pairs of dFPFH values calculated on the partial query and the target object. Global shape similarity is derived by means of a weighted distance of Fisher vectors. Local and global distances are derived for multiple scales and are being combined to obtain a ranked list of the most similar complete 3D objects. Experiments on the large-scale benchmark dataset for partial object retrieval of the shape retrieval contest (SHREC) 2013, as well as on the publicly available Hampson pottery dataset, support improved performance of the proposed method against seven recently evaluated retrieval methods.
A Spatio-Temporal Descriptor for Dynamic 3D Facial Expression Retrieval and Recognition
(The Eurographics Association, 2015) Danelakis, Antonios; Theoharis, Theoharis; Pratikakis, Ioannis; I. Pratikakis and M. Spagnuolo and T. Theoharis and L. Van Gool and R. Veltkamp
The recent availability of dynamic 3D facial scans has spawned research activity in recognition based on such data. However, the problem of facial expression retrieval based on dynamic 3D facial data has hardly been addressed and is the subject of this paper. A novel descriptor is created, capturing the spatio-temporal deformation of the 3D facial mesh sequence. Experiments have been implemented using the standard BU - 4DFE dataset. The obtained retrieval results exceed the state-of-the-art results and the new descriptor is much more frugal in terms of space requirements. Furthermore, a methodology which exploits the retrieval results, in order to achieve unsupervised dynamic 3D facial expression recognition is presented, in order to directly compare the proposed descriptor against the wealth of works in recognition. The aforementioned unsupervised methodology outperforms the supervised dynamic 3D facial expression recognition state-of-the-art techniques in terms of classification accuracy.
SymPan: 3D Model Pose Normalization via Panoramic Views and Reflective Symmetry
(The Eurographics Association, 2013) Sfikas, Konstantinos; Pratikakis, Ioannis; Theoharis, Theoharis; Umberto Castellani and Tobias Schreck and Silvia Biasotti and Ioannis Pratikakis and Afzal Godil and Remco Veltkamp
A novel pose normalization method, based on panoramic views and reflective symmetry, is presented. Initially, the surface of a 3D model is projected onto the lateral surface of a circumscribed cylinder, aligned with the primary principal axis of space. Based on this cylindrical projection, a normals' deviation map is extracted and using an octree-based search strategy, the rotation which optimally aligns the primary principal axis of the 3D model and the cylinder's axis is computed. The 3D model's secondary principal axis is then aligned with the secondary principal axis of space in a similar manner. The proposed method is incorporated in a hybrid scheme, that serves as the pose normalization method in a state-of-the-art 3D model retrieval system. The effectiveness of this system, using the hybrid pose normalization scheme, is evaluated in terms of retrieval accuracy and the results clearly show improved performance against current approaches.
Temporal Ensemble of Shape Functions
(The Eurographics Association, 2014) Brkic, Karla; Aldomà, Aitor; Vincze, Markus; Segvic, Sinisa; Kalafatic, Zoran; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
This paper proposes novel descriptors that integrate information from multiple views of a 3D object, called Temporal Ensemble of Shape Functions (TESF) descriptors. The TESF descriptors are built by combining per-view Ensemble of Shape Functions (ESF) descriptors with Spatio-Temporal Appearance (STA) descriptors. ESF descriptors provide a compact representation of ten different shape functions per object view (obtained by virtually rendering the object from different viewpoints), and STA descriptors efficiently combine ESF descriptors of multiple object views. The proposed descriptors are evaluated on two publicly available datasets, the 3D-Net database and the Princeton Shape Benchmark. They provide a good performance on both datasets, similar to that of the Spherical Harmonic Descriptor (SHD), with the advantage that because of their view-based nature the TESF descriptors might prove useful for the problem of object classification from limited viewpoints. Such property is of special interest in robotics where the agent is able to move around the object to improve single-view results.

Browse

Browsing 3DOR: Eurographics Workshop on 3D Object Retrieval by Subject "Applications"

Results Per Page

Sort Options