3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage and engineering. Current approaches either try to optimize a non‐data‐driven surface representation to fit the points, or learn a data‐driven prior over the distribution of commonly occurring surfaces and how they correlate with potentially noisy point clouds. Data‐driven methods enable robust handling of noise and typically either focus on a global or a local prior, which trade‐off between robustness to noise on the global end and surface detail preservation on the local end. We propose PPSurf as a method that combines a global prior based on point convolutions and a local prior based on processing local point cloud patches. We show that this approach is robust to noise while recovering surface details more accurately than the current state‐of‐the‐art. Our source code, pre‐trained model and dataset are available at https://github.com/cg‐tuwien/ppsurf.
Players may cease from playing a chosen gamesooner than expected for many reasons. One of the mostimportant is related to the way game designers and developerscalibrate game challenge levels. In practice, players havedifferent skill levels and may find usual predetermined difficultlevels as too easy or too hard, becoming frustrated or bored. The result may be decreased motivation to keep on playingthe game, which means reduced engagement. An approachto mitigate this issue is dynamic game difficulty balancing(DGB), which is a process that adjusts gameplay parametersin real-time according to the current player skill level. Inthis paper we propose a real-time solution to DGB usingEvolutionary Fuzzy Cognitive Maps, for dynamically balancinga game difficulty, helping to provide a well balanced level ofchallenge to the player. Evolutionary Fuzzy Cognitive Maps arebased on concepts that represent context game variables andare related by fuzzy and probabilistic causal relationships thatcan be updated in real time. We discuss several simulationexperiments that use our solution in a runner type game tocreate more engaging and dynamic game experiences.
Due to the advancement of computing and the power of the new hardware, more economical, it is now feasible to have thousands of images which can be analyzed to allow classification for its shape and/or color. Furthermore, techniques and efficiency of the classification depends on the characteristics to be obtained of images in order to compare and classify them according to their similarity. Some images, such as model cars, planes and boats, can be discriminated by their shape. However, other images such as butterfly species where the shape is similar, the color plays an important role in the discrimination task. In this research we propose a novel approach to extract distinctive features of images by combining the HSV color model and wavelets filters. Furthermore, we investigate the best combination of features color and form. Experiments have shown improved performance by combining the HSV color model with Gabor wavelets.
14 February 2014 in International Journal of Computer Applications
Fuzzy Cognitive Maps (FCM) is a paradigm used to represent knowledge in a simple and concise way, expressing the grade of relation that exists between concepts and causal relationships. Due to its flexibility, FCM has been successfully applied in numerous applications in diverse research fields, such as, robotics, medical diagnosis, decision problems in information technology, games, and so forth. However, one critical drawback is the determination of the weights in the representation graph, which is generally done by an expert. The present paper proposes a semi-automated method for calibrating the weights in a solution for the problem of dynamic game difficulty balancing (DGB) using Evolutionary Fuzzy Cognitive Maps (E-FCM). The proposed algorithm adjusts the weights in real time, ensuring an equilibrium between the values generated according to the expert’s contribution (based on a static analysis) and the changes produced in the values of the concepts by the calibration process during the simulation (a dynamic analysis).