Hyper-Realist Rendering: A Theoretical Framework

arXiv (Cornell University) · 2024 · 1 citations

• Computer Science
• Artificial Intelligence
• Computer Science

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.

An Interactive Web-Based System for Creating Single Panel Cartoons with Visually Valid Compositions

arXiv (Cornell University) · 2023

• Computer Science
• Computer Science
• Artificial Intelligence

The creation of cartoon-based stories (comics) requires a lot of creativity and hard work for naive users. We observe that single-panel cartoons are the building blocks of any comic story. To develop a strong comic story, it is critical to obtain visually valid single panels. In this work, we have developed a methodology to guarantee the placement of characters to obtain a valid cartoon frame based on the methods used by professional cartoonists. Using this methodology, we have developed a web-based system to create single-panel cartoons from a given set of character images. We have made this system available in GitHub as open-source so that this basic single-panel cartoon can be used as infrastructure to develop more complex structures. Our web-based system for single-panel cartoons can be viewed at http://storytelling.viz.tamu.edu.

Design of architectured materials based on topological and geometrical interlocking

Journal of Materials Research and Technology · 2021 · 52 citations

• Computer Science
• Materials science
• Computer Science

In this article we present a design principle based on segmenting a structure into a set of topologically or geometrically interlocked elements. None of these designs was borrowed from Nature and yet there are some parallels between these structures born in the minds of researchers and Nature's designs. We give some historical background, describe the different kinds of interlocking structures, and discuss the ways in which they can be generated. Based on the beneficial features of the proposed structures, such as a great tolerance to local failures, enhanced bending compliance, high sound and energy absorption, ease of assembly and disassembly, and nearly full recyclability, we discuss possible applications of the concept of topological and geometrical interlocking design.

Generalized abeille tiles: Topologically interlocked space-filling shapes generated based on fabric symmetries

Computers & Graphics · 2020 · 38 citations

• Computer Science
• Computer Science
• Artificial Intelligence

Deep Learning

Computer · 2020 · 101 citations

• Computer Science
• Computer Science
• Artificial Intelligence

Various puzzles, quizzes, games, humorous definitions, or mathematical that should engage the interest of readers.