CompAesth 10: Workshop on Computational Aesthetics
Permanent URI for this collection
Browse
Browsing CompAesth 10: Workshop on Computational Aesthetics by Subject "Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Picture/Image Generation-Display algorithms"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Realtime Aesthetic Image Retargeting(The Eurographics Association, 2010) Liu, Ligang; Jin, Yong; Wu, Qingbiao; Pauline Jepp and Oliver DeussenHumans have always sought to achieve aesthetics in art. In this paper, we present a novel approach for retargeting images to different aspect ratios while improving the composition aesthetics of the results. A simpler computational aesthetic energy is proposed and used to drive the salient objects and prominent lines to move towards their corresponding optimal positions. A mesh-based warping scheme is presented to transform the images while protecting the visual appearance of salient objects. The objective function is quadratic and thus it can be quickly minimized by solving a sparse linear system. The retargeting results are generated in realtime while the user changes the aspect ratios of the target images. A variety of experiments have shown the applicability and effectiveness of our algorithm.Item A Robust and Universal Gradient Domain Imaging Solver Using Gradient Variables and Locally Varying Metrics(The Eurographics Association, 2010) Neumann, László; Hegedüs, Ramón; Pauline Jepp and Oliver DeussenGradient Domain Imaging (GDI) has gained a high importance and provoked numerous powerful applications over the last decade. It employs a workflow of creating an inconsistent gradient field (GF) from one or more images using different non-linear operations and finally it determines an image with a consistent, integrable GF that falls near to the prescribed inconsistent one. However, the result is not really predictable, often suffers from halo-effects and other local distortions at higher frequencies as well as from uncontrollable far-effects arising from local gradient-contradictions. The unfolding of these artifacts culminates in an undesired overall image appearance. None of the common GDI solvers can overcome these side-effects as they utilize the same local isotropic 'coefficient-pattern' in a sparse matrix description and they differ only in the numerical solution techniques. We present a powerful GDI method solving the problem completely in the gradient domain with gradient-variables and using spatially varying metrics that depends only on the starting inconsistent gradient field. After obtaining the nearest consistent gradient field with the pre-defined metrics we return into the image space by double integration that yields the wanted pixel intensity values. Our method delivers a great aesthetic enhancement by eliminating halo effects and saving small details, furthermore providing a realistic and pleasant overall light distribution at lower frequencies. By significantly extending the range of allowed inconsistency in the prescribed gradient field, it also allows for solving a large class of problems that proved hopeless beforehand.