arXiv subjects

Ergun Akleman

Publications and source records attributed to Ergun Akleman.

At least 19 recordsLinked to original sources

arXiv2026

Hybrid Intelligence in Cartoon Captioning: Evaluating AI as a Creative Writing Partner

Crafting cartoon captions requires an understanding of humor, context, and the relationship between image and text. Traditionally, illustrators and writers collaborate to strengthen visual storytelling and comedic timing. With advances in natural language generation, Large Language Models (LLMs) can assist in this process. This study examines AI's role in caption generation by testing GPT-4o via the ChatGPT interface on IEEE Computer magazine cartoons. By removing captions and prompting AI to generate replacements, we assess its ability to produce jokes that match the depicted situation and narrative intent. Our findings show that while AI-generated captions are often humorous and contextually relevant, they sometimes diverge from the cartoon's intended meaning, for example, by missing irony, cultural references, or contextual constraints. However, AI can also produce alternatives that broaden creative exploration and occasionally improve upon the original humor. We argue that current AI systems are best used as an assistant rather than a replacement for human creativity. By integrating AI-generated suggestions, cartoonists can explore diverse humor styles, streamline ideation, and refine final captions while retaining creative control. This study highlights AI's potential as a practical tool for caption ideation within a hybrid human-AI workflow.

cs.HC↗

arXiv2026

Twisted Edges: A Unified Framework for Designing Linked Knot (LK) Structures Using Labeled Non-Manifold Surface Meshes

We present Twisted Edges, a unified framework for designing Linked Knot (LK) structures using labeled non-manifold surface meshes. While the concept of edge twists, originating in topological graph theory, is foundational to these designs, prior approaches have been strictly limited to binary states. We identify this restriction as a critical barrier; binary twisting fails to capture the full spectrum of topological possibilities, rendering a vast class of structural and dynamic behaviors inaccessible. To overcome this limitation, we generalize the twist formulation to support arbitrary integer twist labels. This expansion reveals that while zero twists may introduce disconnections, applying even twists to 2-manifold meshes robustly preserves connectivity, transforming surfaces into fully connected, chainmail-like structures where faces form consistently linked cycles. Furthermore, we extend this framework to non-manifold meshes, where specific integer assignments prevent cycle merging. This capability, unattainable with binary methods, enables the design of partial connectivity and functional hinges, supporting dynamic folding and articulation. Theoretically, we show that these integer-twisted meshes correspond to knotted surfaces in four dimensions, with LK structures arising as their immersions into $\mathbb{R}^3$. By breaking the binary constraint, this work establishes a coherent paradigm for the systematic exploration of previously unstudied woven and articulated structures.

cs.GR↗

arXiv2025

Comparing Human and AI Performance in Visual Storytelling through Creation of Comic Strips: A Case Study

This article presents a case study comparing the capabilities of humans and artificial intelligence (AI) for visual storytelling. We developed detailed instructions to recreate a three-panel Nancy cartoon strip by Ernie Bushmiller and provided them to both humans and AI systems. The human participants were 20-something students with basic artistic training but no experience or knowledge of this comic strip. The AI systems used were popular commercial models trained to draw and paint like artists, though their training sets may not necessarily include Bushmiller's work. Results showed that AI systems excel at mimicking professional art but struggle to create coherent visual stories. In contrast, humans proved highly adept at transforming instructions into meaningful visual narratives.

cs.HC↗

arXiv2024

Medial Parametrization of Arbitrary Planar Compact Domains with Dipoles

We present medial parametrization, a new approach to parameterizing any compact planar domain bounded by simple closed curves. The basic premise behind our proposed approach is to use two close Voronoi sites, which we call dipoles, to construct and reconstruct an approximate piecewise-linear version of the original boundary and medial axis through Voronoi tessellation. The boundaries and medial axes of such planar compact domains offer a natural way to describe the domain's interior. Any compact planar domain is homeomorphic to a compact unit circular disk admits a natural parameterization isomorphic to the polar parametrization of the disk. Specifically, the medial axis and the boundary generalize the radial and angular parameters, respectively. In this paper, we present a simple algorithm that puts these principles into practice. The algorithm is based on the simultaneous re-creation of the boundaries of the domain and its medial axis using Voronoi tessellation. This simultaneous re-creation provides partitions of the domain into a set of "skinny" convex polygons wherein each polygon is essentially a subset of the medial edges (which we call the spine) connected to the boundary through exactly two straight edges (which we call limbs). This unique structure enables us to convert the original Voronoi tessellation into quadrilaterals and triangles (at the poles of the medial axis) neatly ordered along the domain boundary, thereby allowing proper parametrization of the domain. Our approach is agnostic to the number of holes and disconnected components bounding the domain. We investigate the efficacy of our concept and algorithm through several examples.

cs.GR↗

arXiv2024

Development of Context-Sensitive Formulas to Obtain Constant Luminance Perception for a Foreground Object in Front of Backgrounds of Varying Luminance

In this article, we present a framework for developing context-sensitive luminance correction formulas that can produce constant luminance perception for foreground objects. Our formulas make the foreground object slightly translucent to mix with the blurred version of the background. This mix can quickly produce any desired illusion of luminance in foreground objects based on the luminance of the background. The translucency formula has only one parameter; the relative size of the foreground object, which is a number between zero and one. We have identified the general structure of the translucency formulas as a power function of the relative size of the foreground object. We have implemented a web-based interactive program in Shadertoy. Using this program, we determined the coefficients of the polynomial exponents of the power function. To intuitively control the coefficients of the polynomial functions, we have used a Bézier form. Our final translucency formula uses a quadratic polynomial and requires only three coefficients. We also identified a simpler affine formula, which requires only two coefficients. We made our program publicly available in Shadertoy so that anyone can access and improve it. In this article, we also explain how to intuitively change the polynomial part of the formula. Using our explanation, users change the polynomial part of the formula to obtain their own perceptively constant luminance. This can be used as a crowd-sourcing experiment for further improvement of the formula.

cs.GR↗

arXiv2024

A Modified de Casteljau Subdivision that Supports Smooth Stitching with Hierarchically Organized Bicubic Bezier Patches

One of the theoretically intriguing problems in computer-aided geometric modeling comes from the stitching of the tensor product Bezier patches. When they share an extraordinary vertex, it is not possible to obtain continuity C1 or G1 along the edges emanating from that extraordinary vertex. Unfortunately, this stitching problem cannot be solved by using higher degree or rational polynomials. In this paper, we present a modified de Casteljau subdivision algorithm that can provide a solution to this problem. Our modified de Casteljau subdivision, when combined with topological modeling, provides a framework for interactive real-time modeling of piecewise smooth manifold meshes with arbitrary topology. The main advantage of the modified subdivision is that the continuity C1 on a given boundary edge does not depend on the positions of the control points on other boundary edges. The modified subdivision allows us to obtain the desired C1 continuity along the edges emanating from the extraordinary vertices along with the desired G1 continuity in the extraordinary vertices.

cs.CG↗

arXiv2024

Projective Holder-Minkowski Colors: A Generalized Set of Commutative & Associative Operations with Inverse Elements for Representing and Manipulating Colors

One of the key problems in dealing with color in rendering, shading, compositing, or image manipulation is that we do not have algebraic structures that support operations over colors. In this paper, we present an all-encompassing framework that can support a set of algebraic structures with associativity, commutativity, and inverse properties. To provide these three properties, we build our algebraic structures on an extension of projective space by allowing for negative and complex numbers. These properties are important for (1) manipulating colors as periodic functions, (2) solving inverse problems dealing with colors, and (3) being consistent with the wave representation of the color. Allowance of negative and complex numbers is not a problem for practical applications, since we can always convert the results into desired range for display purposes as we do in High Dynamic Range imaging. This set of algebraic structures can be considered as a generalization of the Minkowski norm Lp in projective space. These structures also provide a new version of the generalized Holder average with associativity property. Our structures provide inverses of any operation by allowing for negative and complex numbers. These structures provide all properties of the generalized Holder average by providing a continuous bridge between the classical weighted average, harmonic mean, maximum, and minimum operations using a single parameter p.

math.NA↗

arXiv2024

On The Power of Subtle Expressive Cues in the Perception of Human Affects

In this study, we introduce a sketch-based method for testing how subtle expressive cues influence the perception of affect in illustrations of human figures. We specifically study the impact of human posture and gaze direction, implicitly specified through nose orientation, on perceived emotions and mood. Through a series of user studies using sketchy illustrations of a running figure, where a professional illustrator manipulated gaze direction through adjustments on the nose orientation, we found that this simple change resulted in a diverse range of perceived affects, spanning from fear to concern and wonder. These findings shed light on the importance of fine details in defining context for context-aware system designs and underscore the importance of recognizing and expressing affect. Understanding minor expressive cues is crucial to developing emotionally intelligent systems capable of expressing affect.

cs.HC↗

arXiv2024

Hyper-Realist Rendering: A Theoretical Framework

This is the first paper in a series on hyper-realist rendering. In this paper, we introduce the concept of hyper-realist rendering and present a theoretical framework to obtain hyper-realist images. We are using the term Hyper-realism as an umbrella word that captures all types of visual artifacts that can evoke an impression of reality. The hyper-realist artifacts are visual representations that are not necessarily created by following logical and physical principles and can still be perceived as representations of reality. This idea stems from the principles of representational arts, which attain visually acceptable renderings of scenes without implementing strict physical laws of optics and materials. The objective of this work is to demonstrate that it is possible to obtain visually acceptable illusions of reality by employing such artistic approaches. With representational art methods, we can even obtain an alternate illusion of reality that looks more real even when it is not real. This paper demonstrates that it is common to create illusions of reality in visual arts with examples of paintings by representational artists. We propose an approach to obtain expressive local and global illuminations to obtain these stylistic illusions with a set of well-defined and formal methods.

cs.GR↗

arXiv2024

Compositing with 2D Vector Fields by using Shape Maps that can represent Inconsistent, Impossible, and Incoherent Shapes

In this paper, we present a new compositing approach to obtain stylized reflections and refractions with a simple control. Our approach does not require any mask or separate 3D rendering. Moreover, only one additional image is sufficient to obtain a composited image with convincing qualitative reflection and refraction effects. We have also developed linearized methods that are easy to compute. Although these methods do not directly correspond to the underlying physical phenomena of reflection and refraction, they can provide results that are visually similar to realistic 3D rendering. The main advantage of this approach is the ability to treat images as ``mock-3D'' shapes that can be inserted into any digital paint system without any significant structural change. The core of our approach is the shape map, which encodes 2D shape and thickness information for all visible points of an image of a shape. This information does not have to be complete or consistent to obtain interesting composites. In particular, the shape maps allow us to represent impossible and incoherent shapes with 2D non-conservative vector fields.

cs.GR↗

arXiv2024

Representing and Modeling Inconsistent, Impossible, and Incoherent Shapes and Scenes with 2D Non-Conservative Vector Fields mapped on 2-Complexes

In this paper, we present a framework to represent mock 3D objects and scenes, which are not 3D but appear 3D. In our framework, each mock-3D object is represented using 2D non-conservative vector fields and thickness information that are mapped on 2-complexes. Mock-3D scenes are simply scenes consisting of more than one mock-3D object. We demonstrated that using this representation, we can dynamically compute a 3D shape using rays emanating from any given point in 3D. These mock-3D objects are view-dependent since their computed shapes depend on the positions of ray centers. Using these dynamically computed shapes, we can compute shadows, reflections, and refractions in real time. This representation is mainly useful for 2D artistic applications to model incoherent, inconsistent, and impossible objects. Using this representation, it is possible to obtain expressive depictions with shadows and global illumination effects. The representation can also be used to convert existing 2D artworks into a Mock-3D form that can be interactively re-rendered.

cs.GR↗

arXiv2023

A Digital Compositing Approach to obtain Animated Chinese Still-life Paintings with Global Effects

In this work, we present a method for turning Chinese still-life paintings with global illumination effects into dynamic paintings with moving lights. Our goal is to preserve the original look and feel of still-life paintings with moving lights and objects. We have developed a deceptively simple method that can be computed as a composite of two animated texture images using an animated rendering. The compositing process can be implemented directly in an animation system such as AfterEffect, which allows for the basic compositing operation over animations. It is also possible to control the colors by changing the material colors in animated rendering. We have provided a proof-of-concept based on an original digital Still-Life painting that is in realist Chinese style. This approach can be used to turn almost any still-life painting into a dynamic painting.

cs.GR↗

arXiv2023

Recursive Camera Painting: A Method for Real-Time Painterly Renderings of 3D Scenes

In this work, we present the recursive camera-painting approach to obtain painterly smudging in real-time rendering applications. We have implemented recursive camera painting as both a GPU-based ray-tracing and in a Virtual Reality game environment. Using this approach, we can obtain dynamic 3D Paintings in real-time. In a camera painting, each pixel has a separate associated camera whose parameters are computed from a corresponding image of the same size. In recursive camera painting, we use the rendered images to compute new camera parameters. When we apply this process a few times, it creates painterly images that can be viewed as real-time 3D dynamic paintings. These visual results are not surprising since multi-view techniques help to obtain painterly effects.

cs.GR↗

arXiv2023

Multi-Axis and Multi-Vector Gradient Estimations: Using Multi-Sampled Complex Unit Vectors to Estimate Gradients of Real Functions

In this preliminary study, we provide two methods for estimating the gradients of functions of real value. Both methods are built on derivative estimations that are calculated using the standard method or the Squire-Trapp method for any given direction. Gradients are computed as the average of derivatives in uniformly sampled directions. The first method uses a uniformly distributed set of axes that consists of orthogonal unit vectors that span the space. The second method only uses a uniformly distributed set of unit vectors. Both methods essentially minimize the error through an average of estimations to cancel error terms. Both methods are essentially a conceptual generalization of the method used to estimate normal fractal surfaces.

math.NA↗

arXiv2023

Web-Based Dynamic Paintings: Real-Time Interactive Artworks in Web Using a 2.5D Pipeline

In this work, we present a 2.5D pipeline approach to creating dynamic paintings that can be re-rendered interactively in real-time on the Web. Using this 2.5D approach, any existing simple painting such as portraits can be turned into an interactive dynamic web-based artwork. Our interactive system provides most global illumination effects such as reflection, refraction, shadow, and subsurface scattering by processing images. In our system, the scene is defined only by a set of images. These include (1) a shape image, (2) two diffuse images, (3) a background image, (4) one foreground image, and (5) one transparency image. A shape image is either a normal map or a height. Two diffuse images are usually hand-painted. They are interpolated using illumination information. The transparency image is used to define the transparent and reflective regions that can reflect the foreground image and refract the background image, both of which are also hand-drawn. This framework, which mainly uses hand-drawn images, provides qualitatively convincing painterly global illumination effects such as reflection and refraction. We also include parameters to provide additional artistic controls. For instance, using our piecewise linear Fresnel function, it is possible to control the ratio of reflection and refraction. This system is the result of a long line of research contributions. On the other hand, the art-directed Fresnel function that provides physically plausible compositing of reflection and refraction with artistic control is completely new. Art-directed warping equations that provide qualitatively convincing refraction and reflection effects with linearized artistic control are also new. You can try our web-based system for interactive dynamic real-time paintings at http://mock3d.tamu.edu/.

cs.GR↗

arXiv2023

Satin Non-Woven Fabrics for Designing of Self-Regulating Breathable Building Skins

In this paper, we introduce the concept of 2-way 2-fold genus-1 non-woven fabrics that can be used to design self-regulating breathable building skins. The advantage of non-woven structures over woven structures for breathable skin design is that they can completely be closed to stop air exchange. We have developed a theoretical framework for such non-woven structures starting from the mathematical theory of biaxial 2-fold Genus-1 woven fabrics. By re-purposing a mathematical notation that is used to describe 2-fold 2-way 2-fold genus-1 woven fabrics, we identify and classify non-woven fabrics. Within this classification, we have identified a special subset that corresponds to satin woven fabrics and allows for maximum air exchange. Any other subset of non-woven structures that correspond to other classical 2-way 2-fold genus-1 fabrics, such as plain or twill, will allow for less air exchange. We also show that there exists another subset of satin non-woven fabrics that can provide the biggest openings.

cond-mat.soft↗

arXiv2023

Moments for Perceptive Narration Analysis Through the Emotional Attachment of Audience to Discourse and Story

In this work, our goal is to develop a theoretical framework that can eventually be used for analyzing the effectiveness of visual stories such as feature films to comic books. To develop this theoretical framework, we introduce a new story element called moments. Our conjecture is that any linear story such as the story of a feature film can be decomposed into a set of moments that follow each other. Moments are defined as the perception of the actions, interactions, and expressions of all characters or a single character during a given time period. We categorize the moments into two major types: story moments and discourse moments. Each type of moment can further be classified into three types, which we call universal storytelling moments. We believe these universal moments foster or deteriorate the emotional attachment of the audience to a particular character or the story. We present a methodology to catalog the occurrences of these universal moments as they are found in the story. The cataloged moments can be represented using curves or color strips. Therefore, we can visualize a character's journey through the story as either a 3D curve or a color strip. We also demonstrated that both story and discourse moments can be transformed into one lump-sum attraction parameter. The attraction parameter in time provides a function that can be plotted graphically onto a timeline illustrating changes in the emotional attachment of audience to a character or the story. By inspecting these functions the story analyst can analytically decipher the moments in the story where the attachment is being established, maintained, strengthened, or conversely where it is languishing.

cs.AI↗

arXiv2023

Curved Space-Filling Tiles Using Voronoi Decomposition with Line, and Curve Segments Closed Under Wallpaper Symmetries

In this paper, we present a new approach to obtain symmetric tiles with curved edges. Our approach is based on using higher-order Voronoi sites that are closed under wallpaper symmetries. The resulting Voronoi tessellations provide us with symmetric tiles with curved edges. We have developed a web application that provides real-time tile design. Our application can be found at https://voronoi.viz.tamu.edu. One of our key findings in this paper is that not all symmetry operations are useful for creating curved tiles. In particular, all symmetries that use mirror operation produce straight lines that are useless for creating new tiles. This result is interesting because it suggests that we need to avoid mirror transformations to produce unusual space-filling tiles in 2D and 3D using Voronoi tessellations.

cs.CG↗