Computer Science

We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, and colors. There are often many possible ways to create a given painting. Our goal is to learn to capture this rich range of possibilities. Creating distributions of long-term videos is a challenge for learning-based video synthesis methods. We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process. We implement this model as a convolutional neural network, and introduce a novel training scheme to enable learning from a limited dataset of painting time lapses. We demonstrate that this model can be used to sample many time steps, enabling long-term stochastic video synthesis. We evaluate our method on digital and watercolor paintings collected from video websites, and show that human raters find our synthetic videos to be similar to time lapse videos produced by real artists. Our code is available at this https URL.

We present an integrated approach for creating and assigning color palettes to different visualizations such as multi-class scatterplots, line, and bar charts. While other methods separate the creation of colors from their assignment, our approach takes data characteristics into account to produce color palettes, which are then assigned in a way that fosters better visual discrimination of classes. To do so, we use a customized optimization based on simulated annealing to maximize the combination of three carefully designed color scoring functions: point distinctness, name difference, and color discrimination. We compare our approach to state-ofthe-art palettes with a controlled user study for scatterplots and line charts, furthermore we performed a case study. Our results show that Palettailor, as a fully-automated approach, generates color palettes with a higher discrimination quality than existing approaches. The efficiency of our optimization allows us also to incorporate user modifications into the color selection process.

We are living in the big data age: An ever increasing amount of data is being produced through data acquisition and computer simulations. While large scale analysis and simulations have received significant attention for cloud and high-performance computing, software to efficiently visualise large data sets is struggling to keep up. Visualization has proven to be an efficient tool for understanding data, in particular visual analysis is a powerful tool to gain intuitive insight into the spatial structure and relations of 3D data sets. Large-scale visualization setups are becoming ever more affordable, and high-resolution tiled display walls are in reach even for small institutions. Virtual reality has arrived in the consumer space, making it accessible to a large audience. This thesis addresses these developments by advancing the field of parallel rendering. We formalise the design of system software for large data visualization through parallel rendering, provide a reference implementation of a parallel rendering framework, introduce novel algorithms to accelerate the rendering of large amounts of data, and validate this research and development with new applications for large data visualization. Applications built using our framework enable domain scientists and large data engineers to better extract meaning from their data, making it feasible to explore more data and enabling the use of high-fidelity visualization installations to see more detail of the data.

This paper proposes a novel framework to evaluate fluid simulation methods based on crowd-sourced user studies in order to robustly gather large numbers of opinions. The key idea for a robust and reliable evaluation is to use a reference video from a carefully selected real-world setup in the user study. By conducting a series of controlled user studies and comparing their evaluation results, we observe various factors that affect the perceptual evaluation. Our data show that the availability of a reference video makes the evaluation consistent. We introduce this approach for computing scores of simulation methods as visual accuracy metric. As an application of the proposed framework, a variety of popular simulation methods are evaluated.

Realistic image synthesis involves computing high-dimensional light transport integrals which in practice are numerically estimated using Monte Carlo integration. The error of this estimation manifests itself in the image as visually displeasing aliasing or noise. To ameliorate this, we develop a theoretical framework for optimizing screen-space error distribution. Our model is flexible and works for arbitrary target error power spectra. We focus on perceptual error optimization by leveraging models of the human visual system's (HVS) point spread function (PSF) from halftoning literature. This results in a specific optimization problem whose solution distributes the error as visually pleasing blue noise in image space. We develop a set of algorithms that provide a trade-off between quality and speed, showing substantial improvements over prior state of the art. We perform evaluations using both quantitative and perceptual error metrics to support our analysis, and provide extensive supplemental material to help evaluate the perceptual improvements achieved by our methods.

Fast and realistic coupling of blood flow and vessel wall is of great importance to virtual surgery. In this paper, we propose a novel data-driven coupling method that formulates physics-based blood flow simulation as a regression problem, using an improved periodic-corrected neural network (PcNet), estimating the acceleration of every particle at each frame to obtain fast, stable and realistic simulation. We design a particle state feature vector based on smoothed particle hydrodynamics (SPH), modeling the mixed contribution of neighboring proxy particles on the blood vessel wall and neighboring blood particles, giving the extrapolation ability to deal with more complex couplings. We present a semi-supervised training strategy to improve the traditional BP neural network, which corrects the error periodically to ensure long term stability. Experimental results demonstrate that our method is able to implement stable and vivid coupling of blood flow and vessel wall while greatly improving computational efficiency.

In this paper alternative method for real-time 3D model rasterization is given. Surfaces are drawn in perspective-map space which acts as a virtual camera lens. It can render single-pass 360° angle of view (AOV) image of unlimited shape, view-directions count and unrestrained projection geometry (e.g. direct lens distortion, projection mapping, curvilinear perspective), natively aliasing-free. In conjunction to perspective vector map, visual-sphere perspective model is proposed. A model capable of combining pictures from sources previously incompatible, like fish-eye camera and wide-angle lens picture. More so, method is proposed for measurement and simulation of a real optical system variable no-parallax point (NPP). This study also explores philosophical and historical aspects of picture perception and presents a guide for perspective design.

Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require a large number of path samples to achieve reliable path guiding. We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples, using an offline trained neural network. We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination. To fully make use of our deep neural network, we partition the scene space into an adaptive hierarchical grid, in which we apply our network to reconstruct high-quality sampling distributions for any local region in the scene. This allows for highly efficient path guiding for any path bounce at any location in path tracing. We demonstrate that our photon-driven neural path guiding method can generalize well on diverse challenging testing scenes that are not seen in training. Our approach achieves significantly better rendering results of testing scenes than previous state-of-the-art path guiding methods.

Creating photorealistic materials for light transport algorithms requires carefully fine-tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge. In the proposed workflow, the user starts with an input image and applies a few intuitive transforms (e.g., colorization, image inpainting) within a 2D image editor of their choice, and in the next step, our technique produces a photorealistic result that approximates this target image. Our method combines the advantages of a neural network-augmented optimizer and an encoder neural network to produce high-quality output results within 30 seconds. We also demonstrate that it is resilient against poorly-edited target images and propose a simple extension to predict image sequences with a strict time budget of 1-2 seconds per image.

Implicit functions provide a fundamental basis to model 3D objects, no matter they are rigid or deformable, in computer graphics and geometric modeling. This paper introduces a new constructive scheme of implicitly-defined 3D objects based on products of implicit functions. This scheme is in contrast with popular approaches like blobbies, meta balls and soft objects, which rely on the sum of specific implicit functions to fit a 3D object to a set of spheres.