Geometry-Aware Neighborhood Search for Learning Local Models for Image Superresolution

Ferreira, Julio Cesar
Vural, Elif
Guillemot, Christine
Local learning of sparse image models has proved to be very effective to solve inverse problems in many computer vision applications. To learn such models, the data samples are often clustered using the K-means algorithm with the Euclidean distance as a dissimilarity metric. However, the Euclidean distance may not always be a good dissimilarity measure for comparing data samples lying on a manifold. In this paper, we propose two algorithms for determining a local subset of training samples from which a good local model can be computed for reconstructing a given input test sample, where we consider the underlying geometry of the data. The first algorithm, called adaptive geometry-driven nearest neighbor search (AGNN), is an adaptive scheme, which can be seen as an out-of-sample extension of the replicator graph clustering method for local model learning. The second method, called geometry-driven overlapping clusters (GOCs), is a less complex nonadaptive alternative for training subset selection. The proposed AGNN and GOC methods are evaluated in image superresolution and shown to outperform spectral clustering, soft clustering, and geodesic distance-based subset selection in most settings.


Extending Correlation Filter-Based Visual Tracking by Tree-Structured Ensemble and Spatial Windowing
Gundogdu, Erhan; Özkan, Huseyin; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2017-11-01)
Correlation filters have been successfully used in visual tracking due to their modeling power and computational efficiency. However, the state-of-the-art correlation filter-based (CFB) tracking algorithms tend to quickly discard the previous poses of the target, since they consider only a single filter in their models. On the contrary, our approach is to register multiple CFB trackers for previous poses and exploit the registered knowledge when an appearance change occurs. To this end, we propose a novel t...
AKTIHANOGLU, M; OZGUC, B; AYKANAT, C (Springer Science and Business Media LLC, 1994-01-01)
This paper describes a system for modeling, animating, previewing and rendering articulated objects. The system has a modeler of objects that consists of joints and segments. The animator interactively positions the articulated object in its stick, control vertex, or rectangular prism representation and previews the motion in real time. Then the data representing the motion and the models is sent to a multicomputer [iPSC/2 Hypercube (Intel)]. The frames are rendered in parallel, exploiting the coherence bet...
Nonlinear dynamic modeling of gear-shaft-disk-bearing systems using finite elements and describing functions
Maliha, R; Dogruer, CU; Özgüven, Hasan Nevzat (ASME International, 2004-05-01)
This study presents a new nonlinear dynamic model for a gear-shaft-disk-bearing system. A nonlinear dynamic model of a spur gear pair is coupled with linear finite element models of shafts carrying them, and with discrete models of bearings and disks. The nonlinear elasticity term resulting from backlash is expressed by a describing function, and a method developed in previous studies to determine multi harmonic responses of nonlinear multi-degree-of-freedom systems is employed for the solution. The excitat...
Good Features to Correlate for Visual Tracking
Gundogdu, Erhan; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2018-05-01)
During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in this family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize the robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learni...
Harmony search based algorithm for the optimum design of grillage systems to LRFD-AISC
Saka, M. P.; ERDAL, FERHAT (Springer Science and Business Media LLC, 2009-03-01)
Harmony search based optimum design method is presented for the grillage systems. This numerical technique imitates the musical performance process that takes place when a musician searches for a better state of harmony. Jazz improvisation seeks to find musically pleasing harmony similar to the optimum design process which seeks to find the optimum solution. The design algorithm considers the serviceability and ultimate strength constraints which are implemented from Load and Resistance Factor Design-Americ...
Citation Formats
J. C. Ferreira, E. Vural, and C. Guillemot, “Geometry-Aware Neighborhood Search for Learning Local Models for Image Superresolution,” IEEE TRANSACTIONS ON IMAGE PROCESSING, pp. 1354–1367, 2016, Accessed: 00, 2020. [Online]. Available: