Computer Science

Heterogeneous object modelling is an emerging area where geometric shapes are considered in concert with their internal physically-based attributes. This paper describes a novel theoretical and practical framework for modelling volumetric heterogeneous objects on the basis of a novel unifying functionally-based hybrid representation called HFRep. This new representation allows for obtaining a continuous smooth distance field in Euclidean space and preserves the advantages of the conventional representations based on scalar fields of different kinds without their drawbacks. We systematically describe the mathematical and algorithmic basics of HFRep. The steps of the basic algorithm are presented in detail for both geometry and attributes. To solve some problematic issues, we have suggested several practical solutions, including a new algorithm for solving the eikonal equation on hierarchical grids. Finally, we show the practicality of the approach by modelling several representative heterogeneous objects, including those of a time-variant nature.

We present a hybrid-driven trajectory prediction method based on group emotion. The data driven and model driven methods are combined to make a compromise between the controllability, generality, and efficiency of the method on the basis of simulating more real crowd movements. A hybrid driven method is proposed to improve the reliability of the calculation results based on real crowd data, and ensure the controllability of the model. It reduces the dependence of our model on real data and realizes the complementary advantages of these two kinds of methods. In addition, we divide crowd into groups based on human relations in society. So our method can calculate the movements in different scales. We predict individual movement trajectories according to the trajectories of group and fully consider the influence of the group movement state on the individual movements. Besides we also propose a group emotion calculation method and our method also considers the effect of group emotion on crowd movements.

There are many applications where users seek to explore the impact of the settings of several categorical variables with respect to one dependent numerical variable. For example, a computer systems analyst might want to study how the type of file system or storage device affects system performance. A usual choice is the method of Parallel Sets designed to visualize multivariate categorical variables. However, we found that the magnitude of the parameter impacts on the numerical variable cannot be easily observed here. We also attempted a dimension reduction approach based on Multiple Correspondence Analysis but found that the SVD-generated 2D layout resulted in a loss of information. We hence propose a novel approach, the Interactive Configuration Explorer (ICE), which directly addresses the need of analysts to learn how the dependent numerical variable is affected by the parameter settings given multiple optimization objectives. No information is lost as ICE shows the complete distribution and statistics of the dependent variable in context with each categorical variable. Analysts can interactively filter the variables to optimize for certain goals such as achieving a system with maximum performance, low variance, etc. Our system was developed in tight collaboration with a group of systems performance researchers and its final effectiveness was evaluated with expert interviews, a comparative user study, and two case studies.

In this paper, we tackle a challenging domain conversion task between photo and icon images. Although icons often originate from real object images (i.e., photographs), severe abstractions and simplifications are applied to generate icon images by professional graphic designers. Moreover, there is no one-to-one correspondence between the two domains, for this reason we cannot use it as the ground-truth for learning a direct conversion function. Since generative adversarial networks (GAN) can undertake the problem of domain conversion without any correspondence, we test CycleGAN and UNIT to generate icons from objects segmented from photo images. Our experiments with several image datasets prove that CycleGAN learns sufficient abstraction and simplification ability to generate icon-like images.

In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set, and maintain a well-paced visual transition from one to the next. In this paper, we propose a conditional GAN morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid-based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self-supervision, our network learns to generate visually pleasing morphing effects featuring believable in-betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.

We present a framework for interactive design of new image stylizations using a wide range of predefined filter blocks. Both novel and off-the-shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify, and tune new styles from a given set of filters. In parallel to this manual design, we propose a novel procedural approach that automatically assembles sequences of filters, leading to unique and novel styles. An important aim of our framework is to allow for interactive exploration and design, as well as to enable videos and camera streams to be stylized on the fly. In order to achieve this real-time performance, we use the \textit{Best Linear Adaptive Enhancement} (BLADE) framework -- an interpretable shallow machine learning method that simulates complex filter blocks in real time. Our representative results include over a dozen styles designed using our interactive tool, a set of styles created procedurally, and new filters trained with our BLADE approach.

Affine transformation, layer blending, and artistic filters are popular processes that graphic designers employ to transform pixels of an image to create a desired effect. Here, we examine various approaches that synthesize new images: pixel-based compositing models and in particular, distributed representations of deep neural network models. This paper focuses on synthesizing new images from a learned representation model obtained from the VGG network. This approach offers an interesting creative process from its distributed representation of information in hidden layers of a deep VGG network i.e., information such as contour, shape, etc. are effectively captured in hidden layers of neural networks. Conceptually, if Φ is the function that transforms input pixels into distributed representations of VGG layers h , a new synthesized image X can be generated from its inverse function, X= Φ −1 (h) . We describe the concept behind the approach, present some representative synthesized images and style-transferred image examples.

We propose a modification to Perlin noise which use computable hash functions instead of textures as lookup tables. We implemented the FNV1, Jenkins and Murmur hashes on Shader Model 4.0 Graphics Processing Units for noise generation. Modified versions of the FNV1 and Jenkins hashes provide very close performance compared to a texture based Perlin noise implementation. Our noise modification enables noise function evaluation without any texture fetches, trading computational power for memory bandwidth.

The connection of edges in a graph generates a structure that is independent of a coordinate system. This visual metaphor allows creating a more flexible representation of data than a two-dimensional scatterplot. In this work, we present STAD (Spanning Trees as Approximation of Data), a dimensionality reduction method to approximate the high-dimensional structure into a graph with or without formulating prior hypotheses. STAD generates an abstract representation of high-dimensional data by giving each data point a location in a graph which preserves the distances in the original high-dimensional space. The STAD graph is built upon the Minimum Spanning Tree (MST) to which new edges are added until the correlation between the distances from the graph and the original dataset is maximized. Additionally, STAD supports the inclusion of additional functions to focus the exploration and allow the analysis of data from new perspectives, emphasizing traits in data which otherwise would remain hidden. We demonstrate the effectiveness of our method by applying it to two real-world datasets: traffic density in Barcelona and temporal measurements of air quality in Castile and León in Spain.

Researchers in the field of connectomics are working to reconstruct a map of neural connections in the brain in order to understand at a fundamental level how the brain processes information. Constructing this wiring diagram is done by tracing neurons through high-resolution image stacks acquired with fluorescence microscopy imaging techniques. While a large number of automatic tracing algorithms have been proposed, these frequently rely on local features in the data and fail on noisy data or ambiguous cases, requiring time-consuming manual correction. As a result, manual and semi-automatic tracing methods remain the state-of-the-art for creating accurate neuron reconstructions. We propose a new semi-automatic method that uses topological features to guide users in tracing neurons and integrate this method within a virtual reality (VR) framework previously used for manual tracing. Our approach augments both visualization and interaction with topological elements, allowing rapid understanding and tracing of complex morphologies. In our pilot study, neuroscientists demonstrated a strong preference for using our tool over prior approaches, reported less fatigue during tracing, and commended the ability to better understand possible paths and alternatives. Quantitative evaluation of the traces reveals that users' tracing speed increased, while retaining similar accuracy compared to a fully manual approach.