科技藝術書報討論

Authors – Ramya Srinivasan, Kanji Uchino

Key words – Generative art, Style transfer, Biases

Abstract – With rapid progress in artificial intelligence (AI), popularity of generative art has grown substantially. From creating paintings to generating novel art styles, AI based generative art has showcased a variety of applications. However, there has been little focus concerning the ethical impacts of AI based generative art. In this work, we investigate biases in the generative art AI pipeline right from those that can originate due to improper problem formulation to those related to algorithm design. Viewing from the lens of art history, we discuss the socio-cultural impacts of these biases. Leveraging causal models, we highlight how current methods fall short in modeling the process of art creation and thus contribute to various types of biases. We illustrate the same through case studies, in particular those related to style transfer. To the best of our knowledge, this is the first extensive analysis that investigates biases in the generative art AI pipeline from the perspective of art history. We hope our work sparks interdisciplinary discussions related to accountability of generative art.

Topic: Only a matter of style: age transformation using a style-based regression model, SIGGRAPH 2021, Session: Technical Papers

Authors: Yuval AlalufTel,  PatashnikTel, et al.

Abstract: 

The task of age transformation illustrates the change of an individual’s appearance over time. Accurately modeling this complex transformation over an input facial image is extremely challenging as it requires making convincing and possibly large changes to facial features and head shape, while still preserving the input identity. In this work, we present an image-to-image translation method that learns to directly encode real facial images into the latent space of a pre-trained unconditional GAN (e.g., StyleGAN) subject to a given aging shift. We employ a pre-trained age regression network used to explicitly guide the encoder in generating the latent codes corresponding to the desired age. In this formulation, our method approaches the continuous aging process as a regression task between the input age and desired target age, providing fine-grained control over the generated image. Moreover, unlike other approaches that operate solely in the latent space using a prior on the path controlling age, our method learns a more disentangled, non-linear path. Finally, we demonstrate that the end-to-end nature of our approach, coupled with the rich semantic latent space of StyleGAN, allows for further editing of the generated images. Qualitative and quantitative evaluations show the advantages of our method compared to state-of-the-art approaches.

Keyword: Style-base Age Manipulation, Generative Adversarial Networks, Age Transformation, Image Editing

Presentation: https://drive.google.com/file/d/1sUkDu0I8EytEhWZEf48MmyR6vqWxlKxU/view?usp=sharing

Paper Link: https://s2021.siggraph.org/session/?sess=sess174

Authors – Huimin Yang, Chulsoo Kim

Key words – Metaverse, Design Trend, Display Space

Abstract – Nowadays, people are paying more and more attention to the ocean, and aquariums are not only used as entertainment spaces, but also take on the important role of spreading marine culture. The metaverse is emerging as an alternative space for meetings in the wake of the new crown outbreak and the shift from offline meetings to online, non-face-to-face methods. As trust in the “virtual” realm increases, so does the scalability of the metaverse and the industries it supports. This thesis analyzes the status of the design of the display space of the world’s representative aquariums and evaluates the viewers’ needs, uses PEST analysis of the external factors in the metaverse environment according to Maslow’s hierarchy of needs, and combines SWOT analysis to investigate and analyze the internal and external environmental factors in the design of the aquarium display space. Finally, we summarized the aspects that can be utilized (OS), need to be improved (OW), need to be monitored (ST) and need to be eliminated (WT).

Art Title: CONVERGENCE

Author: Desmond Lo

Art Statement: 最近於 K11 Art Mall 的 chi K11 Art Space 就正舉辦「虛實幻境 Wonder-verse——Artzioneer 元宇宙體驗空間 Pop-Up」（下簡稱 Wonder-verse）的展覽，由成立不久的 NFT 平台 Artzioneer 籌辦，主題就正是「進入元宇宙」，並邀請了十一位本地藝術家圍繞這個主題創作了一系列的 NFT 作品，展覽入口放置的就是香港著名動畫設計師 Desmond Lo 的作品《CONVERGENCE》，以 3D 動畫重現一個充斥着霓虹燈的街境，並以接近2米高的投影方式呈現。

PPT

Topic: All One Needs to Know about Metaverse:
A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021)

Authors: Lee, L. H., Braud, T., Zhou, P., Wang, L., Xu, D., Lin, Z., … & Hui, P.

Abstract: Since the popularisation of the Internet in the 1990s, the cyberspace has kept evolving. We have created various computer-mediated virtual environments including social networks, video conferencing, virtual 3D worlds (e.g., VR Chat), augmented reality applications (e.g., Pokemon Go), and Non-Fungible Token Games (e.g., Upland). Such virtual environments, albeit non-perpetual and unconnected, have bought us various degrees of digital transformation. The term `metaverse’ has been coined to further facilitate the digital transformation in every aspect of our physical lives. At the core of the metaverse stands the vision of an immersive Internet as a gigantic, unified, persistent, and shared realm. While the metaverse may seem futuristic, catalysed by emerging technologies such as Extended Reality, 5G, and Artificial Intelligence, the digital `big bang’ of our cyberspace is not far away. This survey paper presents the first effort to offer a comprehensive framework that examines the latest metaverse development under the dimensions of state-of-the-art technologies and metaverse ecosystems, and illustrates the possibility of the digital `big bang’. First, technologies are the enablers that drive the transition from the current Internet to the metaverse.

Keyword: Metaverse, Immersive Internet, Augmented/Virtual Reality, Avatars, Artificial Intelligence, Digital Twins, Networking and Edge Computing, Virtual Economy, Privacy and Social Acceptability.

Class Presentation

Paper Source: https://arxiv.org/abs/2110.05352

Title: Leveraging NVIDIA Omniverse for In Situ Visualization

Author: Mathias Hummel(B) and Kees van Kooten  NVIDIA, Santa Clara, USA{mathiash,kvankooten}@nvidia.com

Keywords:

In situ visualization, NVIDIA Omniverse, ParaView, Catalys

Abstract: “Omniverse is NVIDIA’s collaboration platform for 3D production pipelines. ”

Abstract:

For Meta world usage in the the form of technical combination, Omniverse provide one of the capable solutions which could combine multiple resource for visual and simulation engines in packages add in the Omniverse.  The usage for the Omniverse provide the performance and efficiency with the tasks work on this service and work with self or group. Some cloud usage and work environment provide the working models in various direction.

PPT File:

Omniverse

Paper from ACM 2021.

Making Up 3D Bodies: Artistic and Serendipitous Modeling of Digital Human Figures

Proceedings of the ACM on Computer Graphics and Interactive Techniques

Volume 4 Issue 2 July 2021 Article No.: 23 pp 1–9

Abstract:

Presentation

Paper

Paper from ACM 2021.

Electrolysis Bubble Display-based Art Installations.

In Fifteenth International Conference on Tangible, Embedded, and Embodied Interaction (TEI ’21), February 14–17, 2021, Salzburg, Austria. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3430524.3440632

Abstract:

“Research was conducted on a digital information display using electrolysis bubbles. “

• The interface displays information as bubbles during the digital signal transition and translates the data as bubbles.
• The various things during this research review the liquid and the bubbles with the time and activities during the data transition.
• The data displayed through the devices contain the digitalized information and optimized the bubbles through various materials when generated the bubbles.

KEYWORDS

Bubble Display; Electrolysis; Water; Art; Ephemeral User Interface

PPT File: Electrolysis Bubble Display

“The Woods”: A Mixed-Reality Two-Player Cooperative Game – ACM SIGGRAPH 2021, Art Paper

→ Full-text Paper

→ Class Presentation

Authors –Kyoung Swearingen et al.

Key words – Cooperative Game, Mixed Reality, Sonic Experience

Abstract – While loneliness in our real lives is increasingly recognized as having dire physical, mental, and emotional consequences, cooperative games have been shown to build empathy and provide positive social impact. In this paper, the authors present “The Woods,” a local cooperative, mixed-reality game using augmented reality and 4-channel audio spatialization panning that provides players with face-to-face interactions in pursuit of a shared goal. This paper discusses the narrative, mechanical, and sonic components of the game, as well as the game’s development process and the players’ experiences. The goal of our team is to develop a narrative-driven AR game that promotes collaborative problem-solving and engages players in an emergent physical and digital experience.

“drop”: An Interactive Art Installation with Water Drop Projection-Mapping, SIGGRAPH 2021, Art Papers

Authors: Sadam Fujioka

Abstract:

This paper describes an interactive art installation titled “drop.” It is the first artwork using the Waterdrop Projection-Mapping (WPM) system, which animates levitating waterdrops. With this artwork, the anno lab team infuses physical characteristics into computer graphics and materializes them as tangible pixels. WPM consists of a waterdrop generator and an ultra high-speed projector. The team uses an ultra high-speed projector to cast stroboscopic spotlights mapping on waterdrops to create an optical illusion of animating each waterdrop individually. This is a new technique to show computer animation by animating levitating waterdrops. This technique explores a new horizon to create animations with tangible pixels that the viewer can touch physically.

Keyword: Interactive Art Installation, Waterdrop Projection Mapping, High Speed Projector, Stroboscopic Effect, Human Computer Interaction

Class Presentation

Publish Link

專題演講：自然之道的現代視野與實踐 （一種傳統調和思維與方法的記述）
演講者：林巖老師
時間：2022年3月29日晚上6:30PM

林巖老師簡介：
1987年開始，經過傳統東方療癒體系知識的學習與沈澱，對傳統民俗療法的領域開始相關的學習。
2005年開始，透過國內外民間傳統療癒認證師資課程內容，做相關的學習。
2016～2019 年間到國際療癒展覽中進行推廣新的療癒產品與系統。使用不同的素材與介質來探討古代與現代的差異性與共同性。
2019年，在越南、中國等地從事 歷史文物、古董、字畫鑑定。
1999年開始，進入科技產業，專注在PC產業與高速訊號領域的產品與研究。

DronePaint: Swarm Light Painting with DNN-based Gesture Recognition – SIGGRAPH 2021, Emerging Technologies

Authors: Valerii Serpiva , Ekaterina Karmanova , Aleksey Fedoseev , Stepan Perminov , Dzmitry Tsetserukou

Abstract:

We propose a novel human-swarm interaction system, allowing the user to directly control a swarm of drones in a complex environment through trajectory drawing with a hand gesture interface based on the DNN-based gesture recognition.

The developed CV-based system allows the user to control the swarm behavior without additional devices through human gestures and motions in real-time, providing convenient tools to change the swarm’s shape and formation. The two types of interaction were proposed and implemented to adjust the swarm hierarchy: trajectory drawing and free-form trajectory generation control.

Keyword: Human-Drone Interaction, Light Painting, Gesture Recognition, Deep Neural Network

Class Presentation

Publish Link

Introduction

“WEIGHTED WALKING: PROPELLER-BASED ON-LEG FORCE SIMULATION OF WALKING IN FLUID MATERIALS IN VR”

Based on some previous studies about the On-Leg activities in VR, this research provided another mindset to understand the Leg activities through their devices.

The devices used and the Applications for VR to implement these mindsets in advance. The overall solutions also reviewed some end-user considerations for the weight and sensor data usage for the VR application.

EmergyTech_Asia_2021

Publish

Frisson Waves: Sharing Frisson to Create Collective Empathetic Experiences for Music Performances

– ACM SIGGRAPH ASIA 2021, Emerging Technologies

Publication

Presentation

Authors: 

Yan He, George Chernyshov, Dingding Zheng, Jiawen Han, Ragnar Thomsen, Danny Hynds, Yuehui Yang, Yun Suen Pai, Kai Kunze, Kouta Minamizawa

Abstract:

We propose Frisson Waves, a real-time system to detect, trigger and share frisson during music performances. The system consists of a physiological sensing wristband for detecting frisson and a thermo-haptic neckband for inducing frisson. This project aims to improve the connectedness of audience members and performers during music performances by sharing frisson. We present the results of an initial concert workshop and a feasibility study of our prototype.