98. AI for Visual Generation

説明

Generative adversarial networks (GANs) have many application areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered `black boxes'. Specifically, the end-users have little control over how to improve editing directions through disentanglement. Prior work focused on new GAN architectures to disentangle editing directions. Alternatively, we propose GANravel --a user-driven direction disentanglement tool that complements the existing GAN architectures and allows users to improve editing directions iteratively. In two user studies with 16 participants each, GANravel users were able to disentangle directions and outperformed the state-of-the-art direction discovery baselines in disentanglement performance. In the second user study, GANravel was used in a creative task of creating dog memes and was able to create high-quality edited images and GIFs.

日本語まとめ

説明

Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and cognitive reflections they may trigger in users. In this paper, we focus on efficiently capturing the elements (i.e., latent semantic relationships) of visual art for personalized recommendation. We propose and study recommender systems based on textual and visual feature learning techniques, as well as their combinations. We then perform a small-scale and a large-scale user-centric evaluation of the quality of the recommendations. Our results indicate that textual features compare favourably with visual ones, whereas a fusion of both captures the most suitable hidden semantic relationships for artwork recommendation. Ultimately, this paper contributes to our understanding of how to deliver content that suitably matches the user's interests and how they are perceived.

日本語まとめ

説明

Hand-drawn sketches and sketch colourization are the most laborious but necessary steps for fashion designers to design exquisite clothes, especially when the fashion design requires distinctive and personal characteristics from designer style. This paper presents an artificial intelligent aided fashion design system, namely StyleMe, to support the automatic generation of clothing sketches with designer style. Given the clothing pictures specified by the designer, StyleMe can use deep learning based generative model to generate clothing sketches that are consistent with the designer style. The system also supports intelligent colourization on clothing sketch by style transfer, according to specified styles from the real fashion images. Through a series of performance evaluations and user studies, we found that our system can generate effective clothing sketches as good as fashion designers' human work, and significantly improve the efficiency of fashion design with its sketch colourization method.

日本語まとめ

説明

Digital painting interfaces require an input fidelity that preserves the artistic expression of the user. Drawing tablets allow for precise and low-latency sensing of pen motions and other parameters like pressure to convert them to fully digitized strokes. A drawback is that those interfaces are rigid. While soft brushes can be simulated in software, the haptic sensation of the rigid pen input device is different compared to using a soft wet brush on paper.

We present InfinitePaint, a system that supports digital painting in Virtual Reality on real paper with a real wet brush. We use special paper that turns black wherever it comes into contact with water and turns blank again upon drying. A single camera captures those temporary strokes and digitizes them while applying properties like color or other digital effects. We tested our system with artists and compared the subjective experience with a drawing tablet.

日本語まとめ

説明

Virtual Reality (VR) applications commonly use the illusion of self-motion (vection) to simulate experiences such as running, driving, or flying. However, this can lead to cybersickness, which diminishes the experience of users, and can even lead to disengagement with this platform.

In this paper we present a study in which we show that users performing a cognitive task while experiencing a VR rollercoaster reported reduced symptoms of cybersickness.

Furthermore, we collected and analysed brain activity data from our participants during their experience using functional near infra-red spectroscopy (fNIRS): \hl{preliminary analysis suggests the possibility} that this technology may be able to detect the experience of cybersickness.

Together, these results can assist the creators of VR experiences, both through mitigation of cybersickness in the design process, and by better understanding the experiences of their users.

日本語まとめ

説明

Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed RePrompt, an automatic method to refine text prompts toward precise expression of the generated images. Inspired by crowdsourced editing strategies, we curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image. With model explanations of the proxy model, we curated a rubric to adjust text prompts to optimize image generation for precise emotion expression. We conducted simulation and user studies, which showed that RePrompt significantly improves the emotional expressiveness of AI-generated images, especially for negative emotions.

日本語まとめ