Rephotography Using Image Collections

This paper proposes a novel system that “rephotographs” a historical photograph with a collection of images. Rather than finding the accurate viewpoint of the historical photo, users only need to take a number of photographs around the target scene. We adopt the structure from motion technique to estimate the spatial relationship among these photographs, and construct a set of 3D point cloud. Based on the user‐specified correspondences between the projected 3D point cloud and historical photograph, the camera parameters of the historical photograph are estimated. We then combine forward and backward warping images to render the result. Finally, inpainting and content‐preserving warping are used to refine it, and the photograph at the same viewpoint of the historical one is produced by this photo collection.     

ProbExplorer: Uncertainty‐guided Exploration and Editing of Probabilistic Medical Image Segmentation

In this paper, we develop an interactive analysis and visualization tool for probabilistic segmentation results in medical imaging. We provide a systematic approach to analyze, interact and highlight regions of segmentation uncertainty. We introduce a set of visual analysis widgets integrating different approaches to analyze multivariate probabilistic field data with direct volume rendering. We demonstrate the user's ability to identify suspicious regions (e.g. tumors) and correct the misclassification results using a novel uncertainty‐based segmentation editing technique. We evaluate our system and demonstrate its usefulness in the context of static and time‐varying medical imaging datasets.     

Data‐driven Handwriting Synthesis in a Conjoined Manner

A person's handwriting appears differently within a typical range of variations, and the shapes of handwriting characters also show complex interaction with their nearby neighbors. This makes automatic synthesis of handwriting characters and paragraphs very challenging. In this paper, we propose a method for synthesizing handwriting texts according to a writer's handwriting style. The synthesis algorithm is composed by two phases. First, we create the multidimensional morphable models for different characters based on one writer's data. Then, we compute the cursive probability to decide whether each pair of neighboring characters are conjoined together or not. By jointly modeling the handwriting style and conjoined property through a novel trajectory optimization, final handwriting words can be synthesized from a set of collected samples. Furthermore, the paragraphs’ layouts are also automatically generated and adjusted according to the writer's style obtained from the same dataset. We demonstrate that our method can successfully synthesize an entire paragraph that mimic a writer's handwriting using his/her collected handwriting samples.     

Real‐Time Temporal‐Coherent Color Contrast Enhancement for Dichromats

We present an automatic image‐recoloring technique for enhancing color contrast for dichromats whose computational cost varies linearly with the number of input pixels. Our approach can be efficiently implemented on GPUs, and we show that for typical image sizes it is up to two orders of magnitude faster than the current state‐of‐the‐art technique. Unlike previous approaches, ours preserve temporal coherence and, therefore, is suitable for video recoloring. We demonstrate the effectiveness of our technique by integrating it into a visualization system and showing, for the first time, real‐time high‐quality recolored visualizations for dichromats.     

Hierarchical Narrative Collage For Digital Photo Album

Collage can provide a summary form on the collection of photos in an album. In this paper, we introduce a novel approach to constructing photo collage in the hierarchical narrative manner. As opposed to previous methods focusing on spatial coherence in the collage layout, our narrative collage arranges the photos according to the basic narrative elements from literary writings, i.e., character, setting and plot. Face, time and place attributes are exploited to embody those narrative elements in the collage. Then, photos are organized into the hierarchical structure for the multi‐level details in the events recorded by the album. Such hierarchical narrative collage can present a visual overview in the chronological order on what happened in the album. Experimental results show that our approach offers a better summarization to browse on the photo album content than previous ones.     

Image Synthesis for Branching Structures

We present a set of techniques for the synthesis of artificial images that depict branching structures like rivers, cracks, lightning, mountain ranges, or blood vessels. The central idea is to build a statistical model that captures the characteristic bending and branching structure from example images. Then a new skeleton structure is synthesized and the final output image is composed from image fragments of the original input images. The synthesis part of our algorithm runs mostly automatic but it optionally allows the user to control the process in order to achieve a specific result. The combination of the statistical bending and branching model with sophisticated fragment‐based image synthesis corresponds to a multi‐resolution decomposition of the underlying branching structure into the low frequency behavior (captured by the statistical model) and the high frequency detail (captured by the image detail in the fragments). This approach allows for the synthesis of realistic branching structures, while at the same time preserving important textural details from the original image.     

Parallel Blue‐noise Sampling by Constrained Farthest Point Optimization

We describe a fast sampling algorithm for generating uniformly‐distributed point patterns with good blue noise characteristics. The method, based on constrained farthest point optimization, is provably optimal and may be easily parallelized, resulting in an algorithm whose performance/quality tradeoff is superior to other state‐of‐the‐art approaches.     

Digital Camouflage Images Using Two‐scale Decomposition

We present an alternative approach to create digital camouflage images which follows human's perception intuition and complies with the physical creation procedure of artists. Our method is based on a two‐scale decomposition scheme of the input images. We modify the large‐scale layer of the background image by considering structural importance based on energy optimization and the detail layer by controlling its spatial variation. A gradient correction is presented to prevent halo artifacts. Users can control the difficulty level of perceiving the camouflage effect through a few parameters. Our camouflage images are natural and have less long coherent edges in the hidden region. Experimental results show that our algorithm yields visually pleasing camouflage images.     

Interactive Learning for Point‐Cloud Motion Segmentation

Segmenting a moving foreground (fg) from its background (bg) is a fundamental step in many Machine Vision and Computer Graphics applications. Nevertheless, hardly any attempts have been made to tackle this problem in dynamic 3D scanned scenes. Scanned dynamic scenes are typically challenging due to noise and large missing parts. Here, we present a novel approach for motion segmentation in dynamic point‐cloud scenes designed to cater to the unique properties of such data. Our key idea is to augment fg/bg classification with an active learning framework by refining the segmentation process in an adaptive manner. Our method initially classifies the scene points as either fg or bg in an un‐supervised manner. This, by training discriminative RBF‐SVM classifiers on automatically labeled, high‐certainty fg/bg points. Next, we adaptively detect unreliable classification regions (i.e. where fg/bg separation is uncertain), locally add more training examples to better capture the motion in these areas, and re‐train the classifiers to fine‐tune the segmentation. This not only improves segmentation accuracy, but also allows our method to perform in a coarse‐to‐fine manner, thereby efficiently process high‐density point‐clouds. Additionally, we present a unique interactive paradigm for enhancing this learning process, by using a manual editing tool. The user explicitly edits the RBF‐SVM decision borders in unreliable regions in order to refine and correct the classification. We provide extensive qualitative and quantitative experiments on both real (scanned) and synthetic dynamic scenes.     

Per‐Vertex Defocus Blur for Stochastic Rasterization

We present user‐controllable and plausible defocus blur for a stochastic rasterizer. We modify circle of confusion coefficients per vertex to express more general defocus blur, and show how the method can be applied to limit the foreground blur, extend the in‐focus range, simulate tilt‐shift photography, and specify per‐object defocus blur. Furthermore, with two simplifying assumptions, we show that existing triangle coverage tests and tile culling tests can be used with very modest modifications. Our solution is temporally stable and handles simultaneous motion blur and depth of field.     

Practical Real‐Time Lens‐Flare Rendering

We present a practical real‐time approach for rendering lens‐flare effects. While previous work employed costly ray tracing or complex polynomial expressions, we present a coarser, but also significantly faster solution. Our method is based on a first‐order approximation of the ray transfer in an optical system, which allows us to derive a matrix that maps lens flare‐producing light rays directly to the sensor. The resulting approach is easy to implement and produces physically‐plausible images at high framerates on standard off‐the‐shelf graphics hardware.     

Multi‐layer Depth Peeling by Single‐Pass Rasterisation for Faster Isosurface Raytracing on GPUs

Empty‐space skipping is an essential acceleration technique for volume rendering. Image‐order empty‐space skipping is not well suited to GPU implementation, since it must perform checks on, essentially, a per‐sample basis, as in kd‐tree traversal, which can lead to a great deal of divergent branching at runtime, which is very expensive in a modern GPU pipeline. In contrast, object‐order empty‐space skipping is extremely fast on a GPU and has negligible overheads compared with approaches without empty‐space skipping, since it employs the hardware unit for rasterisation. However, previous object‐order algorithms have been able to skip only exterior empty space and not the interior empty space that lies inside or between volume objects. In this paper, we address these issues by proposing a multi‐layer depth‐peeling approach that can obtain all of the depth layers of the tight‐fitting bounding geometry of the isosurface by a single rasterising pass. The maximum count of layers peeled by our approach can be up to thousands, while maintaining 32‐bit float‐point accuracy, which was not possible previously. By raytracing only the valid ray segments between each consecutive pair of depth layers, we can skip both the interior and exterior empty space efficiently. In comparisons with 3 state‐of‐the‐art GPU isosurface rendering algorithms, this technique achieved much faster rendering across a variety of data sets.     

Topological Landscape Ensembles for Visualization of Scalar‐Valued Functions

Visual representation techniques enable perception and exploration of scientific data. Following the topological landscapes metaphor of Weber et al., we provide a new algorithm for visualizing scalar functions defined on simply connected domains of arbitrary dimension. For a potentially high dimensional scalar field, our algorithm produces a collection of, in some sense complete, two‐dimensional terrain models whose contour trees and corresponding topological persistences are identical to those of the input scalar field. The algorithm exactly preserves the volume of each region corresponding to an arc in the contour tree. We also introduce an efficiently computable metric on terrain models we generate. Based on this metric, we develop a tool that can help the users to explore the space of possible terrain models.     

Contrast‐aware Halftoning

This paper proposes two variants of a simple but efficient algorithm for structure‐preserving halftoning. Our algorithm extends Floyd‐Steinberg error diffusion; the goal of our extension is not only to produce good tone similarity but also to preserve structure and especially contrast, motivated by our intuition that human perception is sensitive to contrast. By enhancing contrast we attempt to preserve and enhance structure also. Our basic algorithm employs an adaptive, contrast‐aware mask. To enhance contrast, darker pixels should be more likely to be chosen as black pixels while lighter pixels should be more likely to be set as white. Therefore, when the positive error is diffused to nearby pixels in a mask, the dark pixels absorb less error and the light pixels absorb more. Conversely, negative error is distributed preferentially to dark pixels. We also propose using a mask with values that drop off steeply from the centre, intended to promote good spatial distribution. It is a very fast method whose speed mainly depends on the size of the mask. But this method suffers from distracting patterns. We then propose a variant on the basic idea which overcomes the first algorithm's shortcomings while maintaining its advantages through a priority‐aware scheme. Rather than proceeding in random or raster order, we sort the image first; each pixel is assigned a priority based on its up‐to‐date distance to black or to white, and pixels with extreme intensities are processed earlier. Since we use the same mask strategy as before, we promote good spatial distribution and high contrast. We use tone similarity, structure similarity, and contrast similarity to validate our algorithm. Comparisons with recent structure‐aware algorithms show that our method gives better results without sacrificing speed.     

Two‐Colored Pixels

In this paper we show how to use two‐colored pixels as a generic tool for image processing. We apply two‐colored pixels as a basic operator as well as a supporting data structure for several image processing applications. Traditionally, images are represented by a regular grid of square pixels with one constant color each. In the two‐colored pixel representation, we reduce the image resolution and replace blocks of N × N pixels by one square that is split by a (feature) line into two regions with constant colors. We show how the conversion of standard mono‐colored pixel images into two‐colored pixel images can be computed efficiently by applying a hierarchical algorithm along with a CUDA‐based implementation. Two‐colored pixels overcome some of the limitations that classical pixel representations have, and their feature lines provide minimal geometric information about the underlying image region that can be effectively exploited for a number of applications. We show how to use two‐colored pixels as an interactive brush tool, achieving realtime performance for image abstraction and non‐photorealistic filtering. Additionally, we propose a realtime solution for image retargeting, defined as a linear minimization problem on a regular or even adaptive two‐colored pixel image. The concept of two‐colored pixels can be easily extended to a video volume, and we demonstrate this for the example of video retargeting.     

A Salience‐based Quality Metric for Visualization

Salience detection is a principle mechanism to facilitate visual attention. A good visualization guides the observer's attention to the relevant aspects of the representation. Hence, the distribution of salience over a visualization image is an essential measure of the quality of the visualization. We describe a method for computing such a metric for a visualization image in the context of a given dataset. We show how this technique can be used to analyze a visualization's salience, improve an existing visualization, and choose the best representation from a set of alternatives. The usefulness of this proposed metric is illustrated using examples from information visualization, volume visualization and flow visualization.     

GuideME: Slice‐guided Semiautomatic Multivariate Exploration of Volumes

Multivariate volume visualization is important for many applications including petroleum exploration and medicine. State‐of‐the‐art tools allow users to interactively explore volumes with multiple linked parameter‐space views. However, interactions in the parameter space using trial‐and‐error may be unintuitive and time consuming. Furthermore, switching between different views may be distracting. In this paper, we propose GuideME: a novel slice‐guided semiautomatic multivariate volume exploration approach. Specifically, the approach comprises four stages: attribute inspection, guided uncertainty‐aware lasso creation, automated feature extraction and optional spatial fine tuning and visualization. Throughout the exploration process, the user does not need to interact with the parameter views at all and examples of complex real‐world data demonstrate the usefulness, efficiency and ease‐of‐use of our method.     

Adaptive Cross‐sections of Anatomical Models

Medical illustrations have been used for a long time for teaching and communicating information for diagnosis or surgery planning. Illustrative visualization systems create methods and tools that adapt traditional illustration techniques to enhance the result of renderings. Clipping the volume is a popular operation in volume rendering for inspecting the inner parts, though it may remove some information of the context that is worth preserving. In this paper we present a new editing technique based on the use of clipping planes, direct structure extrusion, and illustrative methods, which preserves the context by adapting the extruded region to the structures of interest of the volumetric model. We will show that users may interactively modify the clipping plane and edit the structures to highlight, in order to easily create the desired result. Our approach works with segmented volume models and non‐segmented ones. In the last case, a local segmentation is performed on‐the‐fly. We will demonstrate the efficiency and utility of our method.     

Real‐time Depth of Field Rendering via Dynamic Light Field Generation and Filtering

We present a new algorithm for efficient rendering of high‐quality depth‐of‐field (DoF) effects. We start with a single rasterized view (reference view) of the scene, and sample the light field by warping the reference view to nearby views. We implement the algorithm using NVIDIA's CUDA to achieve parallel processing, and exploit the atomic operations to resolve visibility when multiple pixels warp to the same image location. We then directly synthesize DoF effects from the sampled light field. To reduce aliasing artifacts, we propose an image‐space filtering technique that compensates for spatial undersampling using MIP mapping. The main advantages of our algorithm are its simplicity and generality. We demonstrate interactive rendering of DoF effects in several complex scenes. Compared to existing methods, ours does not require ray tracing and hence scales well with scene complexity.     

HyperMoVal: Interactive Visual Validation of Regression Models for Real‐Time Simulation

During the development of car engines, regression models that are based on machine learning techniques are increasingly important for tasks which require a prediction of results in real‐time. While the validation of a model is a key part of its identification process, existing computation‐ or visualization‐based techniques do not adequately support all aspects of model validation. The main contribution of this paper is an interactive approach called HyperMoVal that is designed to support multiple tasks related to model validation: 1) comparing known and predicted results, 2) analyzing regions with a bad fit, 3) assessing the physical plausibility of models also outside regions covered by validation data, and 4) comparing multiple models. The key idea is to visually relate one or more n‐dimensional scalar functions to known validation data within a combined visualization. HyperMoVal lays out multiple 2D and 3D sub‐projections of the n‐dimensional function space around a focal point. We describe how linking HyperMoVal to other views further extends the possibilities for model validation. Based on this integration, we discuss steps towards supporting the entire workflow of identifying regression models. An evaluation illustrates a typical workflow in the application context of car‐engine design and reports general feedback of domain experts and users of our approach. These results indicate that our approach significantly accelerates the identification of regression models and increases the confidence in the overall engineering process.