Browsing by Subject "3D scenes"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Open Access Alignment of uncalibrated images for multi-view classification(IEEE, 2011) Arık, Sercan Ömer; Vuraf, E.; Frossard P.Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pair-wise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of images is necessary prior to distance computation. We propose a method for the registration of uncalibrated images that capture the same 3D scene or object. We model the depth map of the scene as an algebraic surface, which yields a warp model in the form of a rational function between image pairs. The warp model is computed by minimizing the registration error, where the registered image is a weighted combination of two images generated with two different warp functions estimated from feature matches and image intensity functions in order to provide robust registration. We demonstrate the flexibility of our alignment method by experimentation on several wide-baseline image pairs with arbitrary scene geometries and texture levels. Moreover, the results on multi-view image classification suggest that the proposed alignment method can be effectively used in graph-based classification algorithms for the computation of pairwise distances where it achieves significant improvements over distance computation without prior alignment. © 2011 IEEE.Item Open Access A clustering-based method to estimate saliency in 3D animated meshes(Elsevier Ltd, 2014) Bulbul, A.; Arpa, S.; Capin, T.We present a model to determine the perceptually significant elements in animated 3D scenes using a motion-saliency method. Our model clusters vertices with similar motion-related behaviors. To find these similarities, for each frame of an animated mesh sequence, vertices' motion properties are analyzed and clustered using a Gestalt approach. Each cluster is analyzed as a single unit and representative vertices of each cluster are used to extract the motion-saliency values of each group. We evaluate our method by performing an eye-tracker-based user study in which we analyze observers' reactions to vertices with high and low saliencies. The experiment results verify that our proposed model correctly detects the regions of interest in each frame of an animated mesh. © 2014 Elsevier Ltd.Item Open Access Infrared digital holography applications for virtual museums and diagnostics of cultural heritage(SPIE, 2011) Paturzo, M.; Pelagotti, A.; Geltrude, A.; Locatelli, M.; Poggi P.; Meucci, R.; Ferraro P.; Stoykova, E.; Yaraş F.; Yöntem, A. Özgür; Kang H.; Onural, LeventInfrared digital holograms of different statuettes are acquired. For each object, a sequence of holograms is recorded rotating the statuette with an angular step of few degrees. The holograms of the moving objects are used to compose dynamic 3D scenes that, then, are optically reconstructed by means of spatial light modulators (SLMs) using an illumination wavelength of 532 nm. This kind of reconstruction allows to obtain a 3D imaging of the statuettes that could be exploited for virtual museums. © 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).Item Open Access Paper and pen: A 3D sketching system(Springer, 2013-10) Yıldız, Cansın; Çapın, TolgaThis paper proposes a method that resembles a natural pen and paper interface to create curve based 3D sketches. The system is particularly useful for representing initial 3D design ideas without much effort. Users interact with the system by the help of a pressure sensitive pen tablet. The input strokes of the users are projected onto a drawing plane, which serves as a paper that they can place anywhere in the 3D scene. The resulting 3D sketch is visualized emphasizing depth perception. Our evaluation involving several naive users suggest that the system is suitable for a broad range of users to easily express their ideas in 3D. We further analyze the system with the help of an architect to demonstrate the expressive capabilities. © 2013 Springer-Verlag London.