Computer Graphics Forum最新文献

Modifying network results is the most intuitive way to inject domain knowledge into network detection algorithms to improve their performance. While advances in computation scalability have made detecting large-scale networks possible, the human ability to modify such networks has not scaled accordingly, resulting in a huge ‘interaction gap’. Most existing works only support navigating and modifying edges one by one in a graph visualization, which causes a significant interaction burden when faced with large-scale networks. In this work, we propose a novel graph pattern mining algorithm based on the minimum description length (MDL) principle to partition and summarize multi-feature and isomorphic sub-graph matches. The mined sub-graph patterns can be utilized as mediums for modifying large-scale networks. Combining two traditional approaches, we introduce a new coarse-middle-fine graph modification paradigm (i.e. query graph-based modification $$ sub-graph pattern-based modification $$ raw edge-based modification). We further present a graph modification system that supports the graph modification paradigm for improving the scalability of modifying detected large-scale networks. We evaluate the performance of our graph pattern mining algorithm through an experimental study, demonstrate the usefulness of our system through a case study, and illustrate the efficiency of our graph modification paradigm through a user study.

Freehand sketch-to-image (S2I) is a challenging task due to the individualized lines and the random shape of freehand sketches. The multi-class freehand sketch-to-image synthesis task, in turn, presents new challenges for this research area. This task requires not only the consideration of the problems posed by freehand sketches but also the analysis of multi-class domain differences in the conditions of a single model. However, existing methods often have difficulty learning domain differences between multiple classes, and cannot generate controllable and appropriate textures while maintaining shape stability. In this paper, we propose a style-guided multi-class freehand sketch-to-image synthesis model, SMFS-GAN, which can be trained using only unpaired data. To this end, we introduce a contrast-based style encoder that optimizes the network's perception of domain disparities by explicitly modelling the differences between classes and thus extracting style information across domains. Further, to optimize the fine-grained texture of the generated results and the shape consistency with freehand sketches, we propose a local texture refinement discriminator and a Shape Constraint Module, respectively. In addition, to address the imbalance of data classes in the QMUL-Sketch dataset, we add 6K images by drawing manually and obtain QMUL-Sketch+ dataset. Extensive experiments on SketchyCOCO Object dataset, QMUL-Sketch+ dataset and Pseudosketches dataset demonstrate the effectiveness as well as the superiority of our proposed method.

We consider a cross field, possibly with singular points of valence 3 or 5, in which all streamlines are finite, and either end on the boundary or form cycles. We show that we can always assign lengths to the two cross field directions to produce an anisotropic orthogonal frame field. There is a one-dimensional family of such length functions, and we optimize within this family so that the two lengths are everywhere as similar as possible. This gives a numerical bound on the minimal anisotropy of any quad mesh exactly following the input cross field. We also show how to remove some limit cycles.

A gerotor pump is a two-piece mechanism where two rotational components, interior and exterior, engage each other via a rotational motion to transfer a fluid in a direction parallel to their rotational axes. A natural question arises on what shape of the gerotor is the optimal one in the sense of maximum fluid being pumped for a unit of time, given the constraint of a fixed material needed to manufacture the pump. As there is no closed-formula to answer this question, we propose a new algorithm to design and optimize the shape of gerotor pumps to be as efficient as possible. The proposed algorithm is based on a fast construction of the envelope of the interior component and subsequent optimization. We demonstrate our algorithm on a benchmark gerotor and show that the optimized solution increases the estimated flowrate by 16%. We also use our algorithm to study the effect of the number of teeth on the cavity area of a gerotor.

Vector sketch software (e.g. Adobe Illustrator, Inkscape) and touch-interactive technologies have long aided artists in the creation of resolution-independent digital drawings that mimic the unconstrained nature of freehand sketches. However, artist intent behind stroke topology is often ambiguous, complicating traditional segmentation tasks such as coloring. For inspiration, we turn to the winding number, a classic geometric property of interest for binary segmentation in the presence of boundary data. Its direct application for multi-region segmentation poses two main challenges: (1) strokes may not be consistently oriented to best identify perceptually salient regions; (2) for interior strokes there is no “correct” orientation, as either choice better distinguishes one of two neighboring regions. Thus, we form a harmonic feature space from multiple winding number fields and perform segmentation via Voronoi/power diagrams in this domain. Our perspective allows both for automatic fill region detection and for a semi-automatic framework that naturally incorporates user hints and interactive sculpting of results, unlike competing automatic methods. Our method is agnostic to curve orientation and gracefully handles varying gap sizes in the sketch boundary, outperforming state-of-the-art colorization methods on these “gappy” inputs. Moreover, it inherits the ability of winding numbers to specify “fuzzy” boundaries, leading to simple strategies for color diffusion and single-parameter-driven growing and shrinking of regions.

We introduce the problem of knot-based inverse perceptual art. Given multiple target images and their corresponding viewing configurations, the objective is to find a 3D knot-based tubular structure whose appearance resembles the target images when viewed from the specified viewing configurations. To solve this problem, we first design a differentiable rendering algorithm for rendering tubular knots embedded in 3D for arbitrary perspective camera configurations. Utilizing this differentiable rendering algorithm, we search over the space of knot configurations to find the ideal knot embedding. We represent the knot embeddings via homeomorphisms of the desired template knot, where the weights of an invertible neural network parametrize the homeomorphisms. Our approach is fully differentiable, making it possible to find the ideal 3D tubular structure for the desired perceptual art using gradient-based optimization. We propose several loss functions that impose additional physical constraints, enforcing that the tube is free of self-intersection, lies within a predefined region in space, satisfies the physical bending limits of the tube material, and the material cost is within a specified budget. We demonstrate through results that our knot representation is highly expressive and gives impressive results even for challenging target images in both single-view and multiple-view constraints. Through extensive ablation study, we show that each proposed loss function effectively ensures physical realizability. We construct a real-world 3D-printed object to demonstrate the practical utility of our approach.