We propose an approach to synthesize textures for the animated free surfaces of fluids. Because fluids deform and experience topological changes, it is challenging to maintain fidelity to a reference texture exemplar while avoiding visual artifacts such as distortion and discontinuities. We introduce an adaptive multiresolution synthesis approach that balances fidelity to the exemplar and consistency with the fluid motion. Given a 2D exemplar texture, an orientation field from the first frame, an animated velocity field, and polygonal meshes corresponding to the animated liquid, our approach advects the texture and the orientation field across frames, yielding a coherent sequence of textures conforming to the per-frame geometry. Our adaptiveness relies on local 2D and 3D distortion measures, which guide multiresolution decisions to resynthesize or preserve the advected content. We prevent popping artifacts by enforcing gradual changes in color over time. Our approach works well both on slow-moving liquids and on turbulent ones with splashes. In addition, we demonstrate good performance on a variety of stationary texture exemplars.

Abstract Stippling is an art style forming images from large numbers of small dots. Computer graphics practitioners have proposed numerous algorithms for stippling and stippling variants over the years. In this paper, we propose a black and white image stylization technique in which the image is formed from heterogeneous black and white vector marks, with stipples and larger regions represented by polygons. Our algorithm applies two passes of stippling: first, we apply stippling to an importance map of the input image; then, using the stipples from the first pass as nodes in a planar graph, we create a binary stippling by labeling each graph node as either black or white using error diffusion. A connected component analysis of the resulting labeling, followed by vectorization of the components, yields a high‐quality black and white representation of the original image. Isolated nodes, sharing a color with none of their neighbors, are akin to stipples; larger groups are polygons. We provide quantitative and qualitative comparisons with previous work on stippling and black and white rendering.

We present an algorithm that creates interesting abstract expressionist images from segments of an input image. The algorithm operates by first segmenting the input image at multiple scales, then redistributing the resulting segments across the image plane to obtain an aesthetic abstract output. Larger segments are placed using neighborhood-aware descriptors, and smaller segments are arranged in a Poisson disk distribution. In our thorough analysis, we show that our results score highly according to several relevant aesthetic metrics, and that our style is indeed abstract expressionism. The results are visually appealing, provided the exemplar has a somewhat diverse color pallette and some amount of structure. • We present a novel algorithm to synthesize attractive abstract images. • We generate abstract expressionist images similar to real ones by aesthetic measures. • Our results differ visually and metrically from their most similar existing artworks.

Unrealistic parser-based dialogue systems limit player agency. Large language model (LLM) characters can enhance agency but lack structure and measurable objectives. In this article, we propose a framework for structured interactions that tracks player progress through specific objectives, while also improving character LLM responses. This approach frames interactions as puzzles with states representing goal-based milestones. We employ an LLM to analyze dialogue history and enforce state transitions for state awareness and to enable specific actions like tailored LLM prompts and multimodal content changes. This results in a robust dialogue state tracking system for goal-based interactions. Using our method, a designer can craft transition rules as abstract goals that allow players to invent their own solutions rather than discovering the designer's intent. We demonstrate this with a hostage scenario game, where the player negotiates with a hostage-taker adversary. The game's effectiveness is assessed through qualitative gameplay analysis and a quantitative evaluation of our state tracking method.

We present an approach to control the animation of liquids. The user influences the simulation by providing a target surface which will be matched by a portion of the liquid at a specific frame of the animation; our approach is also effective for multiple target surfaces forming an animated sequence. A source simulation provides the context liquid animation with which we integrate the controlled target elements. From each target frame, we compute a target simulation in two parts, one forward and one backward, which are then joined together. The particles for the two simulations are initially placed on the target shape, with velocities sampled from the source simulation. The backward particles use velocities in the opposite direction as the forward simulation, so that the two halves join seamlessly. When there are multiple target frames, each target frame simulation is computed independently, and the particles from these multiple target simulations are later combined. In turn, the target simulation is joined to the source simulation. Appropriate steps are taken to select which particles to keep when joining the forward, backward, and source simulations. This results in an approach where only a small fraction of the computation time is devoted to the target simulation, allowing faster computation times as well as good turnaround times when designing the full animation. Source and target simulations are computed using an off-the-shelf Lagrangian simulator, making it easy to integrate our approach with many existing animation pipelines. We present test scenarios demonstrating the effectiveness of the approach in achieving a well-formed target shape, while still depicting a convincing liquid look and feel.

In this paper we present StyleBin—an approach to example-based stylization of videos that can produce consistent binocular depiction of stylized content on stereoscopic displays. Given the target sequence and a set of stylized keyframes accompanied by information about depth in the scene, we formulate an optimization problem that converts the target video into a pair of stylized sequences, in which each frame consists of a set of seamlessly stitched patches taken from the original stylized keyframe. The aim of the optimization process is to align the individual patches so that they respect the semantics of the given target scene, while at the same time also following the prescribed local disparity in the corresponding viewpoints and being consistent in time. In contrast to previous depth-aware style transfer techniques, our approach is the first that can deliver semantically meaningful stylization and preserve essential visual characteristics of the given artistic media. We demonstrate the practical utility of the proposed method in various stylization use cases.

Recently, there has been an upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer (NST). However, the state of performance evaluation in this field is poor, especially compared to the norms in the computer vision and machine learning communities. Unfortunately, the task of evaluating image stylisation is thus far not well defined, since it involves subjective, perceptual, and aesthetic aspects. To make progress towards a solution, this paper proposes a new structured, three-level, benchmark dataset for the evaluation of stylised portrait images. Rigorous criteria were used for its construction, and its consistency was validated by user studies. Moreover, a new methodology has been developed for evaluating portrait stylisation algorithms, which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces. We perform evaluation for a wide variety of image stylisation methods (both portrait-specific and general purpose, and also both traditional NPR approaches and NST) using the new benchmark dataset.

Abstract We propose an approach to synthesise a texture on an animated fluid free surface using a distortion metric combined with a feature map. Our approach is applied as a post‐process to a fluid simulation. We advect deformable patches to move the texture along the fluid flow. The patches are covering the whole surface every frame of the animation in an overlapping fashion. Using lapped textures combined with deformable patches, we successfully remove blending artifact and rigid artifact seen in previous methods. We remain faithful to the texture exemplar by removing distorted patch texels using a patch erosion process. The patch erosion is based on a feature map provided together with the exemplar as inputs to our approach. The erosion favors removing texels toward the boundary of the patch as well as texels corresponding to more distorted regions of the patch. Where texels are removed leaving a gap on the surface, we add new patches below existing ones. The result is an animated texture following the velocity field of the fluid. We compared our results with recent work and our results show that our approach removes ghosting and temporal fading artifacts.

We propose a region-based abstraction of a photograph, where the image plane is covered by overlapping irregularly shaped regions that approximate the image content. We segment regions using a novel region growth algorithm intended to produce highly irregular regions that still respect image edges, different from conventional segmentation methods that encourage compact regions.

Abstract We propose an approach for temporally coherent patch‐based texture synthesis on the free surface of fluids. Our approach is applied as a post‐process, using the surface and velocity field from any fluid simulator. We apply the texture from the exemplar through multiple local mesh patches fitted to the surface and mapped to the exemplar. Our patches are constructed from the fluid free surface by taking a subsection of the free surface mesh. As such, they are initially very well adapted to the fluid's surface, and can later deform according to the free surface velocity field, allowing a greater ability to represent surface motion than rigid or 2D grid‐based patches. From one frame to the next, the patch centers and surrounding patch vertices are advected according to the velocity field. We seek to maintain a Poisson disk distribution of patches, and following advection, the Poisson disk criterion determines where to add new patches and which patches should e flagged for removal. The removal considers the local number of patches: in regions containing too many patches, we accelerate the temporal removal. This reduces the number of patches while still meeting the Poisson disk criterion. Reducing areas with too many patches speeds up the computation and avoids patch‐blending artifacts. The final step of our approach creates the overall texture in an atlas where each texel is computed from the patches using a contrast‐preserving blending function. Our tests show that the approach works well on free surfaces undergoing significant deformation and topological changes. Furthermore, we show that our approach provides good results for many fluid simulation scenarios, and with many texture exemplars. We also confirm that the optical flow from the resulting texture matches the fluid velocity field. Overall, our approach compares favorably against recent work in this area.

Digital mosaics have usually used regular tiles, simulating historical tessellated mosaics. In this paper, we present a method for synthesizing pebble mosaics, a historical mosaic style in which the tiles are rounded pebbles. We address both the tiling problem, of distributing pebbles over the image plane so as to approximate the input image content, and the problem of geometry, creating a smooth rounded shape for each pebble. We adopt simple linear iterative clustering (SLIC) to obtain elongated tiles conforming to image content, and smooth the resulting irregular shapes into shapes resembling pebble cross-sections. Then, we create an interior and exterior contour for each pebble and solve a Laplace equation over the region between them to obtain height-field geometry. The resulting pebble set approximates the input image while representing full geometry that can be rendered and textured for a highly detailed representation of a pebble mosaic.

This paper investigates contrast enhancement as an approach to tone reduction, aiming to convert a photograph to black and white. Using a filter-based approach to strengthen contrast, we avoid making a hard decision about how to assign tones to segmented regions. Our method is inspired by sticks filtering, used to enhance medical images but not previously used in non-photorealistic rendering. We amplify contrast of pixels along the direction of greatest local difference from the mean, strengthening even weak features if they are most prominent. A final thresholding step converts the contrast-enhanced image to black and white. Local smoothing and contrast enhancement balances abstraction and structure preservation; the main advantage of our method is its faithful depiction of image detail. Our method can create a set of effects: line drawing, hatching, and black and white, all having superior details to previous black and white methods.

We propose guiding vectors to augment graph-based tree synthesis, in which trees are collections of least-cost paths in a graph. Each node has an associated guiding vector; edges parallel to the guiding vector are cheap, but edges are more expensive when their orientation differs from the guiding vector. We further propose an incremental method for assigning guiding vectors over the graph, in which a node's guiding vector is an incremental rotation of that of its parent. We present a complete procedural system for tree modeling; our use of guiding vectors enables the graph-based method to produce high-quality tree models resembling a variety of real-world tree species.

In this paper we propose that what-you-know authentication schemes be built using narrative elements. Specifically, we propose that stories be used as the basis of memory-based user authentication, rather than use a fixed string as the secret for authentication (as is the case with text passwords and PINs). The insight here is that secure text passwords are ``boring'' and, hence, are hard to remember. Narrative is, in contrast, extremely memorable, forming the basis of much of human communication. We present a simple, implementable scheme for narrative authentication using text adventures. We then also examine other strategies for generating and testing knowledge of narrative.

Abstract 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.

In this paper, we present an improvement to the minimum error boundary cut, a method of shaping texture patches for non-parametric texture synthesis from example algorithms such as Efros and Freeman's Image Quilting [4]. Our method uses an alternate distance metric for Dijkstra's algorithm [3], and as a result we are able to prevent the path from taking short cuts through high cost areas, as can sometimes be seen in traditional image quilting. Furthermore, our method is able to reduce both the maximum error in the resulting texture and the visibility of the remaining defects by spreading them over a longer path. Post-process methods such as pixel re-synthesis [9] can easily be modified and applied to our minimum boundary cut to increase the quality of the results.

Abstract We present a physically inspired model of wax crayons, which synthesizes drawings from collections of user‐specified strokes. Paper is represented by a height‐field texture, and a crayon is modeled with a 2D mask that evolves as it interacts with the paper. The amount of wax deposition is computed based on the crayon contact profile, contact force and friction. Previously deposited wax is smeared by crayon action, based on wax softness and contact information. Deposited wax can also be carved from the paper by the crayon and redeposited at another location. The distributed wax is rendered using a simplified Kubelka–Monk model, which approximates light transmission and scattering effects.

We present a physically-inspired model of wax crayons, which synthesizes drawings from collections of user-specified strokes. Paper is represented by a height-field texture, and a crayon is modeled with a 2D mask that evolves as it interacts with the paper. The amount of wax deposition is computed based on the crayon contact profile, contact force, and friction. Previously deposited wax is smeared by crayon action, based on wax softness and contact information. The distributed wax is rendered using a simplified Kubelka-Monk model, which approximates light transmittance and scattering effects.