1,721,126 research outputs found
View Synthesis From A Single Uncalibrated Image
No full textThis paper presents a method for generating synthetic views of a soccer ground starting from a single uncali- brated image. The relative affine structure of the players is computed by exploiting the knowledge of the soccer ground geometry and the fact that the players are in vertical positions. Then, novel views are generated using the “plane+parallax” representation to reproject points
Robust deformation capture from temporal range data for surface rendering
No full textImagine an object such as a paper sheet being waved in front of some sensor. Reconstructing the time-varying 3D shape of the object finds direct applications in computer animation. The goal of this paper is to provide such a deformation capture system for surfaces. It uses temporal range data obtained by sensors such as those based on structured light or stereo. So as to deal with many different kinds of material, we do not make the usual assumption that the object surface has textural information. This rules out those techniques based on detecting and matching keypoints or directly minimizing color discrepancy. The proposed method is based on a planar mesh that is deformed so as to fit each of the range images. We show how to achieve this by minimizing a compound cost function combining several data and regularization terms, needed to make the overall system robust so that it can deal with low quality datasets. Carefully examining the parameter to residual relationship shows that this cost function can be minimized very efficiently by coupling nonlinear least squares methods with sparse matrix operators. Experimental results for challenging datasets coming from different kinds of range sensors are reported. The algorithm is reasonably fast and is shown to be robust to missing and erroneous data points
Local signature quantization by sparse coding
No full textIn 3D object retrieval it is very important to define reliable shape descriptors, which compactly characterizegeometric properties of the underlying surface. To this aim two main approaches are considered: global, andlocal ones. Global approaches are effective in describing the whole object, while local ones are more suitableto characterize small parts of the shape. Some strategies to combine these two approaches have been proposedrecently but still no consolidate work is available in this field. With this paper we address this problem and proposea new method based on sparse coding techniques. A set of local shape descriptors are collected from the shape.Then a dictionary is trained as generative model. In this fashion the dictionary is used as global shape descriptorfor shape retrieval purposes. Preliminary experiments are performed on a standard dataset by showing a drasticimprovement of the proposed method in comparison with well known local-to-global and global approaches
A sparse coding approach for local-to-global 3D shape description
No full textThe definition of reliable shape descriptors is an essential topic for 3D object retrieval. In general, two main approaches are considered: global, and local. Global approaches are effective in describing the whole object, while local ones are more suitable to characterize small parts of the shape. Recently some strategies to combine these two approaches have been proposed which are mainly concentrated to the so-called bag of words paradigm. With this paper we address this problem and propose an alternative strategy that goes beyond the bag of word approach. In particular, a sparse coding technique is exploited for the 3Ddomain: a set of local shape descriptors are collected fromthe shape, and then a dictionary is trained as generativemodel. In this fashion the dictionary is used as global shapedescriptor for shape retrieval purposes. Several experimentsare performed on standard databases in order to evaluate theproposed method in challenging situations like the case of‘SHREC 2011: robustness benchmark’ where strong shapetransformations are included, and the case of ‘SHREC 2007:partial matching track’ where composite models are consideredin the query phase. A drastic improvement of theproposed method is observed by showing that sparse codingapproach is particularly suitable for local-to-global descriptionand outperforms other approaches such as the bag ofwords
Free energy score spaces: using generative information in discriminative classifiers
Full text linkA score function induced by a generative model of the data can provide a feature vector of a fixed dimension for eachdata sample. Data samples themselves may be of differing lengths (e.g., speech segments, or other sequential data), but as ascore function is based on the properties of the data generation process, it produces a fixed-length vector in a highly informativespace, typically referred to as “score space”. Discriminative classifiers have been shown to achieve higher performances inappropriately chosen score spaces with respect to what is achievable by either the corresponding generative likelihood-basedclassifiers, or the discriminative classifiers using standard feature extractors. In this paper, we present a novel score space thatexploits the free energy associated with a generative model. The resulting free energy score space (FESS) takes into accountthe latent structure of the data at various levels, and can be shown to lead to classification performance that at least matchesthe performance of the free energy classifier based on the same generative model, and the same factorization of the posterior.We also show that in several typical computer vision and computational biology applications the classifiers optimized in FESSoutperform the corresponding pure generative approaches, as well as a number of previous approaches combining discriminatingand generative models
A functional skeleton transfer
No full textThe animation community has spent significant effort trying to ease rigging procedures. This is necessitated because the increasing availability of 3D data makes manual rigging infeasible. However, object animations involve understanding elaborate geometry and dynamics, and such knowledge is hard to infuse even with modern data-driven techniques. Automatic rigging methods do not provide adequate control and cannot generalize in the presence of unseen artifacts. As an alternative, one can design a system for one shape and then transfer it to other objects. In previous work, this has been implemented by solving the dense point-to-point correspondence problem. Such an approach requires a significant amount of supervision, often placing hundreds of landmarks by hand. This paper proposes a functional approach for skeleton transfer that uses limited information and does not require a complete match between the geometries. To do so, we suggest a novel representation for the skeleton properties, namely the functional regressor, which is compact and invariant to different discretizations and poses. We consider our functional regressor a new operator to adopt in intrinsic geometry pipelines for encoding the pose information, paving the way for several new applications. We numerically stress our method on a large set of different shapes and object classes, providing qualitative and numerical evaluations of precision and computational efficiency. Finally, we show a preliminar transfer of the complete rigging scheme, introducing a promising direction for future explorations
- …
