2010 Proceeding- Program Chairs:
- Mohamed Doudi,
- Michela Spagnuolo,
- Remco Veltkamp
- Sponsor:
- sigmm
3D media has emerged rapidly as a new type of content within the multimedia domain. The recent acceleration of 3D content production, witnessed across all fields up to user-generated content, is causing a huge amount of traffic and data stored and transmitted using Internet technologies. Recent advances in 3D acquisition and 3D graphics rendering technologies boosted the creation of 3D model archives for several application domains. These include archaeology and cultural heritage, computer-assisted design (CAD), medicine and bioinformatics, 3D face recognition and security, entertainment and serious gaming, spatial data and 3D city management.
Search engines will soon become a key interaction tool for engaging with this data deluge, and 3D content-based retrieval methods will be crucial in the development of effective 3D search engines: visual media are meant to be seen and should be searched accordingly.
3D content-based retrieval is attracting researchers from different fields: computer vision, computer graphics, machine learning, human-computer interaction, and the semantic web. Since 2008, a series of workshops specifically devoted to the topic was initiated under the auspices of the Eurographics association. The first EG 3D Object Retrieval (3DOR) workshop took place in Crete, April 2008, followed by 3DOR'09 in Munich, March 2009, and 3DOR'10 in Nörkopping, May 2010. The response of the community in all these years was encouraging in terms of number of submission and attendance rate. Due to the co-location of the 3DOR workshop with the Eurographics conference, the events primarily addressed the computer graphics community.
Now, the co-location with ACM Multimedia 2010, the worldwide premier multimedia conference, gave us the opportunity to meet the multimedia community and further promote a cross-fertilization ground that hopefully will stimulate further discussions on the next steps in this important research area. The response to the call for participation was a success: even if scheduled shortly after the EG 3DOR'10 workshop, the ACM 3DOR'10 received 24 full paper submissions on various topics related to 3D retrieval, ranging from new indexing methods for generic 3D models to context-specific methods, such as face recognition and molecular data analysis. Out of the 24 submissions received, 7 contributions were accepted as oral papers (acceptance rate 30%), and 7 as poster papers.
The ACM 3DOR'10 workshop will feature a one-day technical programme, with the presentation of the full papers and poster session. The invited talk given by Prof. Anuj Srivastava on Elastic Riemannian Frameworks and Statistical Tools for Shape Analysis complements the programme.
Proceeding Downloads
Elastic Riemannian frameworks and statistical tools for shape analysis
Interest in shapes of 3D objects naturally leads to shape analysis of curves and surfaces. The theme of this talk is Riemannian frameworks that offer certain distinct advantages. In addition to providing measures for shape comparisons, clustering and ...
Local visual patch for 3d shape retrieval
We present a novel method for 3D-object retrieval using Bag of Feature (BoF) approaches [8]. The method starts by selecting and then describing a set of points from the 3D-object. The proposed descriptor is an indexed collection of closed curves in R3 ...
3D shape retrieval based on best view selection
We describe the preliminary results of an ongoing work on content-based 3D retrieval, based on the selection of the best view of 3D objects according to semantic criteria. Experiments show that a single view is sufficient to achieve good performance, if ...
Orientation invariant 3D object classification using hough transform based methods
In comparison to the 2D case, object class recognition in 3D is a much less researched area. However, with the advent of affordable 3D acquisition technology and the growing popularity of 3D content, its relevance is steadily increasing. Just as in the ...
Single spin image-ICP matching for efficient 3D object recognition
A robust and efficient method is presented for recognizing objects in unstructured 3D point clouds acquired from photos. The method first finds the locations of target objects using single spin image matching and then retrieves the orientation and ...
3D face landmark labelling
Most 3D face processing systems require feature detection and localisation, for example to crop, register, analyse or recognise faces. The three features often used in the literature are the tip of the nose, and the two inner corner of the eyes. Failure ...
Shape comparison through mutual distances of real functions
Spectral analysis provides a library of shape description elements intrinsically defined by the shape itself.
Among all, the eigenfunctions of the Laplace-Beltrami operator can be thought as a set of real valued functions that implicitly abstract and ...
Volumetric heat kernel signatures
Invariant shape descriptors are instrumental in numerous shape analysis tasks including deformable shape comparison, registration, classification, and retrieval. Most existing constructions model a 3D shape as a two-dimensional surface describing the ...
A benchmark for best view selection of 3D objects
The best view selection corresponds to the task of automatically selecting the most representative view of a 3D model. In this paper, we describe a benchmark for evaluation of best view selection algorithms. The benchmark consists of the preferred views ...
Incorporating several features in the protein ray descriptor for more accurate protein 3D structure retrieval
The retrieval of protein structures is one of the most popular topics in bioinformatics community nowadays, since it can be further used for determining protein function. With the technology innovation, the number of protein tertiary structures ...
Unique shape context for 3d data description
The use of robust feature descriptors is now key for many 3D tasks such as 3D object recognition and surface alignment. Many descriptors have been proposed in literature which are based on a non-unique local Reference Frame and hence require the ...
Distance metric learning and feature combination for shape-based 3D model retrieval
This paper proposes a 3D model retrieval algorithm that employs an unsupervised distance metric learning with a combination of appearance-based features; two sets of local visual features and a set of global features. These visual features are extracted ...
Indexing of 3d models based on graph of surfacic regions
We present a search engine dedicated to 3D object databases. The originality of the method is to represent models by adjacency graphs of surfacic regions. After segmentation of the 3D surface of a model, regions are described by various shape ...
Elastic radial curves to model 3D facial deformations
In this paper we study the challenging problem of 3D face recognition in presence of facial expressions. Therefore, the facial surfaces are represented by an indexed collections of radial curves on them, emanating from the nose tips. Facial shapes ...
Recognition of 3D faces with missing parts based on profile networks
3D face recognition solutions proposed so far compare face scans of a probe subject against archived face scans (gallery), assuming the entire scans are available for both probe and gallery. Though the assumption is reasonable for subjects in the ...
Cited By
-
Jiang B, Ma Y, He F, Xu K, Wan J, Chen S and Qin W (2021). HUSC: a local feature descriptor of point cloud based on hemisphere neighborhood International Conference on Signal Image Processing and Communication (ICSIPC 2021), 10.1117/12.2600154, 9781510645400, (17)
-
den Hollander R, van der Stap N, Wilmer M, Dijk J, Hickman D and Bürsing H (2019). Vessel track summarization by viewpoint selection Electro-Optical and Infrared Systems: Technology and Applications XVI, 10.1117/12.2535679, 9781510630215, (32)
-
Vlaminck M, Luong H and Philips W (2018). Have I Seen This Place Before? A Fast and Robust Loop Detection and Correction Method for 3D Lidar SLAM, Sensors, 10.3390/s19010023, 19:1, (23)
-
Baskurt A, Sitnik R, Hachani M, Ouled Zaid A and Puech W (2014). 3D mesh indexing based on structural analysis IS&T/SPIE Electronic Imaging, 10.1117/12.2042755, , (901305), Online publication date: 6-Mar-2014.
- Proceedings of the ACM workshop on 3D object retrieval
Recommendations
ACM workshop on 3d object retrieval: 3DOR'10 chair's welcome
MM '10: Proceedings of the 18th ACM international conference on Multimedia3D media has emerged rapidly as a new type of content within the multimedia domain. The recent acceleration of 3D content production, witnessed across all fields up to user-generated content, is causing a huge amount of traffic and data stored and ...