Abstract

Abstract
We propose a solution for generating dynamic heightmap data to simulate deformations for soft objects, with a focus on the human skin. The solution utilizes mesostructure-level wrinkles and procedural textures to add static microstructure details. It offers flexibility beyond human skin during animations to mimic other material deformations, such as leather and rubber. Various methods suffer from self-intersections and increased storage requirements during synthesizing wrinkles. Although manual intervention using wrinkles and tension maps offers control, it lacks information on principal deformation directions. Physics-based simulations can generate detailed wrinkle maps, but may limit artistic control. Our research presents a procedural method to enhance the generation of dynamic deformation patterns, including wrinkles, with better control and without reliance on captured data. Incorporating static procedural patterns improves realism, and the proposed approach can be used in other application areas. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Abstract

Abstract
In this study we explore the impact of multisensory stimuli in virtual reality on users' emotional responses, addressing a knowledge gap in this rapidly evolving field. Utilizing a range of sensory inputs, including taste, haptics, and smell, in addition to audiovisual cues, this study aims to understand how different combinations of these stimuli affect the users' emotional experience. Two immersive virtual experiences have been developed for this purpose. One included a scenario to evoke positive emotions through selectively chosen pleasant multisensory stimuli, validated in a focus group. The other sought the contrary: to trigger negative emotions by integrating selected combinations of unpleasant multisensory stimuli, also validated in the same focus group. Through a comparative analysis, our findings revealed significant differences in emotional responses between the groups exposed to positive and negative stimuli combinations. Results indicated that combinations involving haptics and taste were particularly effective in eliciting intense emotions using positive stimuli, but their impact was less significant with negative stimuli. This investigation suggests that a fully multisensory virtual environment integrating positive stimuli might lead to cognitive overload, reducing overall emotional responses. In contrast, environments with negative stimuli could enhance emotional engagement and be more likely to avoid cognitive overload. These findings have important implications for designing emotionally resonant and compelling virtual reality experiences. This research enhances the understanding of sensory integration in virtual reality and its effects on emotional engagement, offering valuable insights for developing more impactful virtual experiences.

Abstract
Creating content for digital video game is an expensive segment of the development process, and many techniques have been explored to automate it. Much of the generated content is graphical, ranging from textures and sprites to typographical elements and user interfaces. Numerous techniques have been explored to automate the generation of these assets, with recent advancements incorporating artificial intelligence methodologies such as deep learning generative models. This study comprehensively surveys the literature from 2016 onwards, focusing on using machine learning to generate image-based assets for video game development, reviewing the deep learning approaches employed, and analyzing the specific challenges found. Specifically, the deep learning approaches employed, the problems addressed within the domain, and the metrics used for evaluating the results. The study demonstrates a knowledge gap in generative methods for some types of video game assets. Additionally, applicability and effectiveness of the most used evaluation metrics in the literature are studied. As future research prospects, with the increase in popularity of generative AI, the adoption of such techniques will be seen in automation processes. © 2018 IEEE.

Abstract
This study discusses the intricate relations between generative artificial intelligence (AI) and music composers. Based on a previous rapid review of recent literature, it reinforces a gap and suggests the need to develop human-centered generative AI design strategies prioritizing cultural artistic (and non-artistic) aspects. We posit that AI-based music generation solutions should resonate with the cultural diversity of stakeholders who are impacted by these systems in practice. The paper highlights the significance of metaphorical design as an effective method in human-AI music co-creation by leveraging familiar interfaces and features that are rooted in everyday objects and cognitive models derived from real-world settings. Our insights illustrate possible ways of (re)framing human-AI metaphorical design to shape perceptions and facilitate seamless interactions between humans and intelligent systems in music co-creativity, particularly at the compositional level. At the heart of this research is the alignment of AI-driven music creation systems with user needs, values, and expectations that vary from culture to culture and thus require a continuous and transparent adaptation of the technology in use to accommodate individual preferences and the socio-algorithmic specificities underlying musicians’ activities.