3DOR 14

Permanent URI for this collection

https://diglib7.eg.org/handle/10.2312/7710

Browse

Now showing 1 - 17 of 17

Coulomb Shapes: Using Electrostatic Forces for Deformation-invariant Shape Representation
(The Eurographics Association, 2014) Boscaini, Davide; Girdziusas, Ramunas; Bronstein, Michael M.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Canonical shape analysis is a popular method in deformable shape matching, trying to bring the shape into a canonical form that undoes its non-rigid deformations, thus reducing the problem of non-rigid matching into a rigid one. The canonization can be performed by measuring geodesic distances between all pairs of points on the shape and embedding them into a Euclidean space by means of multidimensional scaling (MDS), which reduces the intrinsic isometries of the shape into the extrinsic (Euclidean) isometries of the embedding space. A notable drawback of MDS-based canonical forms is their sensitivity to topological noise: different shape connectivity can affect dramatically the geodesic distances, resulting in a global distortion of the canonical form. In this paper, we propose a different shape canonization approach based on a physical model of electrostatic repulsion.We minimize the Coulomb energy subject to the local distance constraints between adjacent shape vertices. Our model naturally handles topological noise, allowing to 'tear' the shape at points of strong repulsion. Furthermore, the problem is computationally efficient, as it lends itself to fast multipole methods. We show experimental results in which our method compares favorably to MDS-based canonical forms.
Large Scale Comprehensive 3D Shape Retrieval
(The Eurographics Association, 2014) Li, B.; Lu, Y.; Li, C.; Godil, A.; Schreck, Tobias; Aono, M.; Chen, Q.; Chowdhury, N. K.; Fang, B.; Furuya, T.; Johan, H.; Kosaka, R.; Koyanagi, H.; Ohbuchi, R.; Tatsuma, A.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
The objective of this track is to evaluate the performance of 3D shape retrieval approaches on a large-scale comprehensive 3D shape database that contains different types of models, such as generic, articulated, CAD and architecture models. The track is based on a new comprehensive 3D shape benchmark, which contains 8,987 triangle meshes that are classified into 171 categories. The benchmark was compiled as a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domainspecific model types. In this track, 14 runs have been submitted by 5 groups and their retrieval accuracies were evaluated using 7 commonly used performance metrics.
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.
TreeSha: 3D Shape Retrieval with a Tree Graph Representation based on the Autodiffusion Function Topology
(The Eurographics Association, 2014) Garro, Valeria; Giachetti, Andrea; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
In this paper we present a new method for shape description and matching based on a tree representation built upon the scale space analysis of maxima of the Autodiffusion function (ADF). The use of the Heat Kernel based approach makes the method invariant to articulated deformations. By coupling maxima of the Autodiffusion function with the related basins of attraction, it is possible to link the information at different scales encoding spatial relationships in a tree structure. Furthermore, texture information can be easily included in the descriptor by adding regional color histograms to the node attributes of the tree. Dedicated graph kernels have been designed to evaluate shape dissimilarity from the obtained representations using both structural, geometric and color information. Preliminary experiments performed on the SHREC 2013 non-rigid textured dataset showed very good retrieval performances.
Manifold Harmonic Transform and Spatial Relationships for Partial 3D Object Retrieval
(The Eurographics Association, 2014) Hoang, Nguyen Vu; Gouet-Brunet, Valérie; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
This paper presents an approach for 3D object retrieval, dedicated to partial shape retrieval in large datasets. A word manipulation, i.e. quantized descriptors, as in the Bag-of-Words representation is employed, based on the extraction of 3D Harris points and on a local description involving local manifold harmonic transform. By adding Δ-TSR, a triangular spatial information between words, the richness and robustness of this representation is reinforced. The approach is invariant to different geometrical transformations of 3D shape such as translation, rotation, scale and robust to shape resolution changes. We have evaluated it in terms of quality of retrieval, facing several state-of-the-art methods and on different public 3D benchmarks involving different contents and degrees of complexity.
Towards the Extraction of Hierarchical Building Descriptions from 3D Indoor Scans
(The Eurographics Association, 2014) Ochmann, Sebastian; Vock, Richard; Wessel, Raoul; Klein, Reinhard; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
We present a new method for the hierarchical decomposition of 3D indoor scans and the subsequent generation of an according hierarchical graph-based building descriptor. The hierarchy consists of four basic levels with according entities, building - storey - room - object. All entities are represented as attributed nodes in a graph and are linked to the upper level entity they are located in. Additionally, nodes of the same level are linked depending on their spatial and topological relationship. The hierarchical description enables easy navigation in the formerly unstructured data, measurement takings, as well as carrying out retrieval tasks that incorporate geometric, topological, and also functional building properties describing e.g. the designated use of single rooms according to the objects it contains. In contrast to previous methods which either focus on the segmentation into rooms or on the recognition of indoor objects, our holistic approach incorporates a rather large spectrum of entities on different semantic levels that are inherent to 3D building representations. In our evaluation we show the feasibility of our method for extraction of hierarchical building descriptions for various tasks using synthetic as well as real world data.
Retrieval and Classification on Textured 3D Models
(The Eurographics Association, 2014) Biasotti, S.; Cerri, A.; Abdelrahman, M.; Aono, M.; Hamza, A. Ben; El-Melegy, M.; Farag, A.; Garro, V.; Giachetti, A.; Giorgi, D.; Godil, A.; Li, C.; Liu, Y.-J.; Martono, H. Y.; Sanada, C.; Tatsuma, A.; Velasco-Forero, S.; Xu, C.-X.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
This paper reports the results of the SHREC'14 track: Retrieval and classification on textured 3D models, whose goal is to evaluate the performance of retrieval algorithms when models vary either by geometric shape or texture, or both. The collection to search in is made of 572 textured mesh models, having a two-level classification based on geometry and texture. Together with the dataset, a training set of 96 models was provided. The track saw eight participants and the submission of 22 runs, to either the retrieval or the classification contest, or both. The evaluation results show a promising scenario about textured 3D retrieval methods, and reveal interesting insights in dealing with texture information in the CIELab rather than in the RGB colour space.
Symmetry and Fourier Descriptor: A Hybrid Feature For NURBS based B-Rep Models Retrieval
(The Eurographics Association, 2014) Dang, Quoc Viet; Morin, Geraldine; Mouysset, Sandrine; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
As the number of models in 3D databases grows, an efficient 3D models indexing mechanism and a similarity measure to ease model retrieval are necessary. In this paper, we present a query-by-model framework for NURBS based B-Rep models retrieval that combines partial symmetry of the object and the Fourier shape descriptor of canonical 2D projections of the 3D models. In fact, most objects are composed by similar parts up to an isometry. By detecting the dominant partial symmetry of a given NURBS based B-Rep model, we define two canonical planes from which the Fourier descriptors are extracted to measure the similarity among 3D models.
Shape Retrieval of Non-Rigid 3D Human Models
(The Eurographics Association, 2014) Pickup, D.; Sun, X.; Rosin, P. L.; Martin, R. R.; Cheng, Z.; Lian, Z.; Aono, M.; Hamza, A. Ben; Bronstein, A.; Bronstein, M.; Bu, S.; Castellani, U.; Cheng, S.; Garro, V.; Giachetti, A.; Godil, A.; Han, J.; Johan, H.; Lai, L.; Li, B.; Li, C.; Li, H.; Litman, R.; Liu, X.; Liu, Z.; Lu, Y.; Tatsuma, A.; J.Ye,; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
We have created a new benchmarking dataset for testing non-rigid 3D shape retrieval algorithms, one that is much more challenging than existing datasets. Our dataset features exclusively human models, in a variety of body shapes and poses. 3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. In this track nine groups have submitted the results of a total of 22 different methods which have been tested on our new dataset.
3D Volume Matching for Mesh Animation of Moving Actors
(The Eurographics Association, 2014) Blache, Ludovic; Loscos, Celine; Nocent, Olivier; Lucas, Laurent; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
4D multiview reconstruction of moving actors has many applications in the entertainment industry and although studios providing such services become more accessible, efforts have to be done in order to improve the underlying technology to produce high-quality 4D contents. In this paper, we enable surface matching for an animated mesh sequence in order to introduce coherence in the data. The context is provided by an indoor multi-camera system which performs synchronized video captures from multiple viewpoints in a chroma key studio. Our input is given by a volumetric silhouette-based reconstruction algorithm that generates a visual hull at each frame of the video sequence. These 3D volumetric models differ from one frame to another, in terms of structure and topology, which makes them very difficult to use in post-production and 3D animation software solutions. Our goal is to transform this input sequence of independent 3D volumes into a single dynamic volumetric structure, directly usable in post-production. These volumes are then transformed into an animated mesh. Our approach is based on a motion estimation procedure. An unsigned distance function on the volumes is used as the main shape descriptor and a 3D surface matching algorithm minimizes the interference between unrelated surface regions. Experimental results, tested on our multiview datasets, show that our method outperforms approaches based on optical flow when considering robustness over several frames.
Quantitative Comparison of Hole Filling Methods for 3D Object Search
(The Eurographics Association, 2014) Rojas, Mario A.; Sukno, Federico M.; Waddington, John L.; Whelan, Paul F.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Retrieval of 3D models has become an important issue due to the increase in the number of digitized objects that are available in many different fields. When stored data present defects such as holes, accurate and reliable repairing tools are needed to solve these issues. In this work we present a comparative evaluation of hole filling algorithms from the local and global perspective, measuring quantitatively the quality of the repaired meshes and describing the impact these tools have on the models. We do this by mapping holes from one mesh onto another in order to create a synthetic dataset with realistic holes and ground truth and use the Hausdorff and RMS distance, as well as the mean angular deviation, to quantify the errors. The results show that the performance at a local level is similar for all compared methods, but large differences (up to 20%) appear when viewed at a global level, where algorithms that use volumetric representations introduce significant changes in the original models.
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.
The Canonically Posed 3D Objects Dataset
(The Eurographics Association, 2014) Papadakis, Panagiotis; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Shape matching methodologies of generic 3D objects are conventionally preceded by a pose normalization stage, that transforms objects to a canonical coordinate frame wherein feature extraction and shape matching is performed. Arguably, the canonical pose of a 3D object depends not only on its geometry but also on its semantic meaning, a characteristic that generally complicates the extraction of ground truth data. This paper introduces the first ground-truth dataset of 3D objects that allows an objective evaluation of methods which obtain the canonical pose of objects within extrinsic space. By virtue of the protocol that was followed to assemble the dataset, 3D objects of the same class share a fixed pose in terms of object center, scale and rotation while undergoing diverse shape deformations. The dataset is publicly disclosed and relevant use cases are discussed.
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.
Extended Large Scale Sketch-Based 3D Shape Retrieval
(The Eurographics Association, 2014) Li, B.; Lu, Y.; Li, C.; Godil, A.; Schreck, Tobias; Aono, M.; Burtscher, M.; Fu, H.; Furuya, T.; Johan, H.; Liu, J.; Ohbuchi, R.; Tatsuma, A.; Zou, C.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
Large scale sketch-based 3D shape retrieval has received more and more attentions in the community of contentbased 3D object retrieval. The objective of this track is to evaluate the performance of different sketch-based 3D model retrieval algorithms using a large scale hand-drawn sketch query dataset on a comprehensive 3D model dataset. The benchmark contains 12,680 sketches and 8,987 3D models, divided into 171 distinct classes. In this track, 12 runs were submitted by 4 groups and their retrieval performance was evaluated using 7 commonly used retrieval performance metrics. We hope that this benchmark, the comparative evaluation results and the corresponding evaluation code will further promote the progress of this research direction for the 3D model retrieval community.
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.
Similarity of Deforming Meshes Based on Spatio-temporal Segmentation
(The Eurographics Association, 2014) Luo, Guoliang; Cordier, Frederic; Seo, Hyewon; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
In this study, we investigate a similarity metric for comparing two deforming meshes. While there have been a large body of works on computing the similarity of static shapes, similarity judgments on deforming meshes are not studied well. Our algorithm uses the degree of deformation to binarily label each triangle in deforming mesh in the spatio-temporal domain, which serves as basis for the spatio-temporal segmentation. The segmentation results are encoded in a form of evolving graph, with an aim of obtaining a compact representation of the motion of the mesh. Finally, we formulate the similarity computation as a sequence matching problem: After clustering similar graphs and assigning each of the graphs with the cluster labels, each deforming mesh is represented with a sequence of labels. Then, we apply a sequence alignment algorithm to compute the locally optimal alignment between the two cluster label sequences, and to compute the similarity metric by normalizing the alignment score. We show that similarities of animation data can be captured correctly by our approach. This may be significant, as it solves a problem that cannot be handled by current approaches.

Browse

Browsing 3DOR 14 by Issue Date

Results Per Page

Sort Options