BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Tokyo X-LIC-LOCATION:Asia/Tokyo BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:JST DTSTART:18871231T000000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260817T171605Z LOCATION:Lobby Gallery (1) & (2)\, G Block\, Level B1 DTSTART;TZID=Asia/Tokyo:20241204T090000 DTEND;TZID=Asia/Tokyo:20241204T180000 UID:siggraphasia_SIGGRAPH Asia 2024_sess196@linklings.com SUMMARY:Posters Gallery DESCRIPTION:At SIGGRAPH Asia 2024, delve into the world of computer graphi cs through the captivating Posters Program. This interactive forum offers a glimpse into the latest ideas and practical contributions from animators , developers, educators, and researchers worldwide.\nEach poster displayed provides valuable insights into various aspects of computer graphics, fro m animation and rendering to machine learning and virtual reality. With a focus on innovation and discovery, attendees can expect to encounter a div erse range of topics that showcase the evolving landscape of CG.\n\nUnder the theme of Curious Minds, this year’s program invites exploration and en courages attendees to engage with emerging trends and technologies. Whethe r you’re seeking behind-the-scenes views of new commercial work or explori ng solutions to challenging problems, the Posters Program offers something for everyone.\n\nJoin us in Tokyo for SIGGRAPH Asia 2024 and witness the latest advancements in computer graphics at the Posters Program.\n\nThese ideas are put together into simple, visually attractive posters showcased at SIGGRAPH Asia. Posters’ authors will also be present to explain their f indings, discuss their work, receive feedback and network with all attende es.\n\n[INDRA] Interactive Deep-dreaming Robotic Artist: Perceived artisti c agency when collaborating with Embodied AI\n\n"INDRA," a painting robot, merges human creativity with AI, exploring the evolving role of human age ncy in co-creation through exchanging painting turns between a user and AI artist on a shared canvas. The system allows us to find a balance between meaningful human control for perceived artistic age...\n\n\nMarina Nakaga wa and Sohei Wakisaka (Keio University Graduate School of Media Design)\n- --------------------\n`Colorblind Game' Can Enhances Awareness of Color Bl indness\n\nThis study explores if a digital game can boost color blindness awareness through the user study with 'color blind' variations of Puyo Pu yo. The results suggest positive effects on awareness.\n\n\nTaiju KIMURA ( Kochi University of Technology) and Hiroki Nishino (University of Bedforsh ire)\n---------------------\n3D Human Pose Estimation Using Ultra-low Reso lution Thermal Images\n\nCan we estimate 3D human pose from 8x8 thermal im ages? Our framework enhances privacy using adversarial learning, ensuring robustness against temperature and subject variations while minimizing per sonal information exposure.\n\n\nTatsuki Arai (Keio University); Mariko Is ogawa (Keio University, JST PRESTO); Kuniharu Sakurada (Keio University, U niversity of Tokyo); and Maki Sugimoto (Keio University)\n---------------- -----\n3D Reconstruction of a Soft Object Surface and Contact Areas in Han d-Object Interactions\n\nIn Hand-Object Interactions (HOIs), contact infor mation between is crucial. We present a preliminary attempt to reconstruct the surface of a soft object and identify the contact area on that surfac e.\n\n\nKohei Miura (Osaka University; Kyoto Research, Sony Computer Scenc e Laboratories, Inc.) and Daisuke Iwai and Kosuke Sato (Osaka University)\ n---------------------\n3D Scene Reconstruction of Point Cloud Data: A Lig htweight Procedural Approach\n\nWe propose a pipeline for the automatic re construction of buildings and facades in the form of procedural grammar de scriptions from raw point cloud data of scenes.\n\n\nVivica Wirth, Max Müh lhäuser, and Alejandro Sanchez Guinea (Technical University of Darmstadt)\ n---------------------\n3D Texture Representation in Projection Mapping on to a Surface with Micro-Vibration\n\nIn projection mapping, we proposed a method of adding depth vibration to the projection target and projecting i mages at high-speed synchronized with the vibration to represent three-dim ensional results.\n\n\nHayase Nishi, Daisuke Iwai, and Kosuke Sato (Osaka University)\n---------------------\n3D-to-2D Animation Smear Effect Techni que Based on Japanese Hand-Drawn Animation Style\n\nOur method achieves th e smear effect in Japanese animation by combining skeletal animation with vertex displacement and bending mechanism. It reduces choppiness by creati ng jagged outlines on fast-moving objects.\n\n\nShu-Ting Lin (Test Researc h, Inc.; National Chengchi University) and Ming-Te Chi (National Chengchi University)\n---------------------\nA Lava Well of Reflexivity: Exploring Speculative Ambient Media\n\nThis work explores ambient media that specula tively integrates reflexive elements to subtly prompt reflection on enviro nmental issues. It challenges perceptions of human impact, aiming to foste r dialogue and awareness.\n\n\nTing Han Daniel Chen (Play Design Lab; Depa rtment of Art&Design, Yuan-Ze University)\n---------------------\nA Method for Generating Tactile Sensations from Textual Descriptions Using Generat ive AI\n\nThis study presents a novel approach to generate tactile sensati ons from text using AI. It combines fingernail sensor data, AudioLDM proce ssing, and ChatGPT-generated onomatopoeia to create diverse haptic feedbac k experiences.\n\n\nMomoka Nakayama, Risako Kawashima, Shintaro Murakami, Yuta Takeuchi, Tatsuya Mori, and Dai Takanashi (Dentsu Lab Tokyo)\n------- --------------\nA Multimodal LLM-based Assistant for User-Centric Interact ive Machine Learning\n\nWe introduce a multimodal LLM-based system that ai ds non-expert users in machine learning development by translating vague u ser needs into concrete task formulations through interactive chat, ensuri ng comprehensive training data.\n\n\nWataru Kawabe and Yusuke Sugano (Univ ersity of Tokyo)\n---------------------\nA Relighting Method for Single Te rrain Image based on Two-stage Albedo Estimation Model\n\nThis paper propo ses a method for relighting a single terrain image to match user-specified times of day or weather conditions by estimating albedo and depth using d eep learning.\n\n\nShun Tatsukawa (Hosei University) and Syuhei Sato (Hose i University, Prometech CG Research)\n---------------------\nA Sentient Sp ace Using Light Sensing with Particle Life\n\nA light-based sensing system enabling dynamic spatial interaction through particle grid projections. T he system captures environmental changes, allowing real-time light adjustm ents, enhancing interactivity and responsiveness within the space.\n\n\nPa n-Pan Shiung and June-Hao Hou (Graduate Institute of Architecture, Nationa l Yang Ming Chiao Tung University)\n---------------------\nA Simple Heat M ethod for Computing Geodesic Paths on General Manifold Representations\n\n We propose a novel algorithm for computing geodesic paths on general manif olds given only the ability to perform closest point queries and 1D heat f low.\n\n\nNathan King (University of Waterloo), Steven Ruuth (Simon Fraser University), and Christopher Batty (University of Waterloo)\n------------ ---------\nA Study of 3D Character Control Methods_Keyboard, Speech, Hand Gesture, and Mixed Interfaces\n\nThis poster presents a pilot study on opt imal usability of desktop interfaces (keyboard, speech, hand gestures) for avatar control in MR-based military training, finding mixed interfaces pr ovide the best usability.\n\n\nJunSeo Park, Hanseob Kim, and Gerard Joungh yun Kim (Korea University)\n---------------------\nAffective Wings: Explor ing Affectionate Behaviors in Close-Proximity Interactions with Soft Float ing Robots\n\nThis study presents “Affective Wings,” a concept involving a soft floating robot designed to enable proximal interactions and physical contact with humans to support emotional connection.\n\n\nMingyang Xu and Yulan Ju (Keio University Graduate School of Media Design); Yunkai Qi (Be ihang University); Xiaru Meng (Keio University Graduate School of Media De sign); Qing Zhang (University of Tokyo); and Matthias Hoppe, Kouta Minamiz awa, Giulia Barbareschi, and Kai Kunze (Keio University Graduate School of Media Design)\n---------------------\nAlive Yi: Interactive Preservation of Yi Minority Embroidery Patterns through Digital Innovation\n\nAlive Yi is an interactive project that uses TouchDesigner and Leap Motion, to pres erve and revitalize the traditional embroidery patterns of the Yi minority (cultural heritage) in China.\n\n\nZhiwei Wang and Yuzhe Xia (Southwest M inzu University); Kexin Nie (University of Sydney); and Mengyao Guo (Shenz hen International School of Design, Harbin Institute of Technology; Univer sity of Macau)\n---------------------\nAn Augmented Reality Experience for Climate Justice: Using Spatial Animation to Enhance Perceived Togethernes s\n\nThis project focuses on designing an AR/MR application for climate ju stice communication. It examines ways to use spatial graphics/animation/so und for multi-user simulations with strategies regarding economic and envi ronmental conflicts.\n\n\nChing-Hua Chuan, Wan-Hsiu Tsai, and Xueer Xia (U niversity of Miami)\n---------------------\nAn Exploratory Study on Fabric ating of Unobtrusive Edible Tags\n\nThis paper explores alternative fabric ation techniques for embedding unobtrusive tags inside foods. We present t wo techniques that do not require food 3D printing, including molding and stamping.\n\n\nYamato Miyatake and Parinya Punpongsanon (Saitama Universit y)\n---------------------\nAn immersive interface for remote collaboration with multiple telepresence robots through digital twin spaces\n\nDev elopment of a smart robot for introduction into nursing care settings. A h uman distributes tasks to the robot from a remote environment, and the rob ot operates according to the instructions.\n\n\nSawa Yoshioka, Shinichi Fu kushige, Mizuki Kawakami, and Kohta Seki (Waseda University)\n------------ ---------\nAnalyzing and Visualizing the Correlation between Ecosystems an d Environmental Sustainability : Focusing on Search API Data\n\nThis study aims to analyze public awareness of environmental sustainability, particu larly focusing on the ecological importance of bees and their impact on hu man food production. Real-time search query data were collected and analyz ed to identify trends related to bees and environmental keywords. Ar...\n\ n\nJungIn Lee (Kyungpook National University)\n---------------------\nAnim ated Pictorial Maps\n\nWe propose a new form of map creation that makes an imated cartography more approachable for non-experts. We focus on improvin g the blending and map style transfer quality.\n\n\nDong-Yi Wu, Li-Kuan Ou , and HuiGuang Huang (National Cheng Kung University); Yu Cao (Hong Kong P olytechnic University, National Cheng Kung University); Xin-Wei Lin (Natio nal Cheng Kung University); Thi-Ngoc-Hanh Le (School of Computer Science a nd Engineering, International University, Ho Chi Minh City, Vietnam; Vietn am National University, Ho Chi Minh City, Vietnam); and Sheng-Yi Yao and T ong-Yee Lee (National Cheng Kung University)\n---------------------\nAnime line art colorization by region matching using region shape\n\nWe propose colorization method for anime line art using reference images. This metho d is considering copyright, and we aim to introduce this method to anime p roduction sites.\n\n\nDaisuke Nanya and Kouki Yonezawa (Meijo University)\ n---------------------\nARAP-Based Shape Editing to Manipulate the Center of Mass\n\nWe propose a method to deform the shape such that the center of mass will match a given target position. Users can manipulate its positio n in interactive speed.\n\n\nShunsuke Hirata (University of Tokyo); Yuta N oma (University of Tokyo, University of Toronto); Koya Narumi (Keio Univer sity, University of Tokyo); and Yoshihiro Kawahara (University of Tokyo)\n ---------------------\nAuditory AR System to Induce Pseudo-Haptic Force Fe edback for Lateral Hand Movements Using Spatially Localized Sound Stimuli\ n\nThis proposal presents a pseudo-force feedback design based on spatiall y localized sound, tailored for the visually impaired. Sound location is a djusted to create an auditory conflict between the perceived hand position in virtual space and its actual position in the real world, thus inducing a forc...\n\n\nDaniel Oswaldo Lopez Tassara, Naoto Wakatsuki, and Keiichi Zempo (University of Tsukuba)\n---------------------\nAutomotive Holograp hic Head-Up Display\n\nAdvanced automotive holographic HUD system : offeri ng 3D holograms, extended virtual image distance (>10m), large field of vi ew (>15 degrees), and wide monocular eye-box (>2cm) for comfortable viewin g experience.\n\n\nJinsu Lee, Keehoon Hong, and Minsik Park (Electronics a nd Telecommunications Research Institute (ETRI))\n---------------------\nB oundary Conditioned Floor Layout Generation with Diffusion Model\n\nUsing self-attention mechanisms, we generate automated floor plans that align wi th exterior wall boundaries. Our approach improves accuracy and produces d iverse, precise vector floor plans over existing GAN methods.\n\n\nYusuke Takeuchi (University of Tokyo; Tetraz, Inc) and Qi An and Atsushi Yamashit a (University of Tokyo)\n---------------------\nBridging Reality and the V irtual Environment: Perceptual Consistency and Visual Adaptation\n\nWe inv estigated perceptual consistency in MR headsets, focusing on brightness an d color. Through psychophysics experiments and model development, we aimed to achieve perceptual consistency and establish color rendering targets.\ n\n\nJun Miao, Alex Shin, Jeanne Vu, Takanori Miki, Guodong Rong, and Josh ua Davis (Meta); Zilong Li (Rochester Institute of Technology); and Wenbin Wang, Jinglun Gao, and Jiangtao Kuang (Meta)\n---------------------\nChor eoSurf: Scalable Surface System with 8-DOF SMA Actuators\n\nThe ChoreoSurf system is a scalable surface system with a shape-memory alloy actuator th at can bend in eight directions. This system can mount actuators on the su rface layers of various threedimensional shapes. Applications include a ta bletop system, interactive wall, tentacles tower, kinetic dress,...\n\n\nA kira Nakayasu (Tokyo Metropolitan University)\n---------------------\nCock tail-Party Communication from a Display to a Synchronized Camera\n\nWe pro pose a Cocktail-Party Communication (CPC) system using display and camera. Utilizing Optical Camera Communication (OCC) technology, we successfully transmitted audio data. Future challenges include distortion correction an d speed enhancement.\n\n\nAsuka Fukubayashi (Sony Semiconductor Solutions Corporation), Mayu Ishii and Yu Nakayama (Tokyo University of Agriculture and Technology), and Shun Kaizu (Sony Semiconductor Solutions Corporation) \n---------------------\nControlling Cross-Content Motion Style Transfer v ia Statistical Style Difference\n\nThis study demonstrates style transfer improvement by a straightforward method to adjust style information obtain ed by Δ𝑆𝑡𝑦𝑙𝑒 which effectively replace original style from a motion conten t to another target style.\n\n\nUsfita Kiftiyani and Seungkyu Lee (Kyung H ee University)\n---------------------\nControlling Diversity in Single-sho t Motion Synthesis\n\nWe propose a VAE-GAN model for the task of controlla ble and diverse motion synthesis from a single motion sample as an alterna tive to the data-dependent modality-to-motion methods.\n\n\nEleni Tselepi (University of Thessaly, Moverse) and Spyridon Thermos, Georgios Albanis, and Anargyros Chatzitofis (Moverse)\n---------------------\nCo-play with D ouble Self: Exploring Bodily-Self Through Heautoscopy-Based XR Hide and S eek Game\n\nIn the hide-and-seek game, what kind of experience or percepti on will be created if a single player plays both the role of the hider and the seeker simultaneously?\n\n\nKezhou Yang and Sohei Wakisaka (Keio Medi a Design)\n---------------------\nCurtain UI: Augmenting Curtains for Tang ible Interactions\n\nTransform everyday curtains into interactive interfac es using capacitive sensing. Curtain UI enables touch-sensitive gestures t o control smart home appliances, offering practical and intuitive embodied interactions.\n\n\nPranshu Anand (IIIT Bangalore, Creative Interfaces Lab - IIIT Delhi) and Vishal Bharti and Anmol Srivastava (Creative Interfaces Lab - IIIT Delhi)\n---------------------\nDeep Learning based Stereo Visi on Camera System\n\nWe present a compact, low-power stereo vision camera s ystem. The system is based on deep learning, operates in real-time, is occ lusion-free, and is robust to a variety of conditions.\n\n\nSunho Ki, Jinh ong Park, Jin-Woo Kim, Rayun Boo, Hyerin Cho, and Hanjun Choi (VisioNexT); Sungmin Woo (Korea University of Technology and Education); and Jeong-Ho Woo (VisioNexT)\n---------------------\nDesign for Hypnotic Line Art Anima tion from a Still Image\n\nStreamline art is a digital art using single-co lor lines to create 3D alike art images. However, manually creating line art animation is time-consuming. We present ideas to create streamline ani mation.\n\n\nXin-Wei Lin, Zhi-Yang Goh, HuiGuang Huang, and Dong-Yi Wu (Na tional Cheng-Kung University); Thi-Ngoc-Hanh Le (School of Computer Scienc e and Engineering, International University, Ho Chi Minh City, Vietnam; Vi etnam National University, Ho Chi Minh City, Vietnam); and Tong-Yee Lee (N ational Cheng-Kung University)\n---------------------\nDesign of Wall Art Utilizing Dynamic Color Changes through Photoelasticity\n\nThis research p resents a dynamic wall art piece using photoelasticity, where color change s occur as polarized light passes through a stretched, transparent, flexib le material. Unlike pixel-based displays such as LCDs and LED matrices, ph otoelasticity creates gentle, organic color transitions with su...\n\n\nRy ota Nakayama, Soshi Takeda, Gakuto Sekine, and Yuichiro Katsumoto (Tokyo D enki University)\n---------------------\nDesigning LLM Response Layouts fo r XR Workspaces in Vehicles\n\nThis study investigates the design of respo nse layouts for large language models in XR environments for vehicle setti ngs.\n\n\nDaun Kim and Jin-Woo Jeong (Seoul National University of Science and Technology)\n---------------------\nDevelopment of Tiny Wireless Posi tion Tracker Enabling Real-Time Intuitive 3D Modeling\n\nThis work impleme nted a wirelessly powered and communicable position tracker in a 10 mm cub ic volume, achieving a 4.75 mm localization error, 10 cm communication ran ge, and an adaptive power receiver providing appropriate voltage for the t racker regardless of the distance between the wireless transm...\n\n\nYuki Maegawa, Masanori Hashimoto, and Ryo Shirai (Kyoto University)\n--------- ------------\nDiskPlay: Dynamic Projection Mapping on Rotating Platforms f or Extended Holographic Display\n\nDiskPlay is an holographic display that uses dynamic projection onto rotating disks. This system provides special visual expressions, such as stereoscopic images, and interactions through manual disk replacement and rotation.\n\n\nHidetaka Katsuyama, Shio Miyaf uji, and Hideki Koike (Institute of Science Tokyo)\n---------------------\ nDisparity Map based Synthetic IR Pattern Augmentation for Active Stereo M atching\n\nWe propose an efficient IR pattern augmentation method using di sparity maps without occlusion test and verify its performance by applying it to deep learning based stereo matching methods.\n\n\nRayun Boo, Jinhon g Park, Jinwoo Kim, Sunho Ki, and Jeong-Ho Woo (VisioNexT)\n-------------- -------\nDualAvatar: Robust Gaussian Avatar with Dual Representation\n\nWe propose DualAvatar, a robust Gaussian Splatting avatar reconstruction met hod that leverages a learnable mesh avatar to achieve more reliable recons truction and rendering of unseen poses from monocular video.\n\n\nJinsong Zhang (Tianjin University, University of Tokyo); I-Chao Shen and Jotaro Sa kamiya (University of Tokyo); Yu-Kun Lai (Cardiff University); Takeo Igara shi (University of Tokyo); and Kun Li (Tianjin University)\n-------------- -------\nDynamically Reconfigurable Paper\n\nOur proposed dynamic paper re defines traditional static paper by transforming it into an interactive me dium, showcasing its potential for creating highly responsive interfaces a nd innovative applications with enhanced user interactivity.\n\n\nRyuhei F uruta, Hikari Kawaguchi, Kazuki Miyasaka, and Mika Sai (University of Elec tro-Communications) and Toshiki Sato (Japan Advanced Institute of Science and Technology (JAIST))\n---------------------\nEchoes of Antiquity: An In teractive Installation for Guqin Culture Heritage Using Mid-Air interacti on and Generative AI\n\n"Echoes of Antiquity" is an interactive installat ion that utilizes Leap Motion for gesture recognition and generative AI fo r image processing to illustrate the symbolic elements of Guqin culture.\n \n\nYuyao Heng, Yingman Chen, and Zihan Gao (Communication University of C hina)\n---------------------\nEfficient Space Variant Gaussian Blur Approx imation\n\nWe propose a novel approximation method to render spatially var ying Gaussian blur's in real time. This has been applied in a web app to a llow for creative image blurring.\n\n\nOliver Richards and Chris Cook (Can va)\n---------------------\nEfficient visualization of appearance space of translucent objects using differential rendering\n\nAn efficient visualiz ation method that allows users to interactively explore the subsurface sca ttering parameter space is presented.\n\n\nRiel Suzuki (Hokkaido Universit y) and Yoshinori Dobashi (Hokkaido University, Prometech CG Research)\n--- ------------------\nEmpathy Engine: Using Game Design and Real-time Techno logy to Cultivate Social Connection\n\nThis VR game simulates the experien ces of takeaway riders, using real-time data to create scenarios that fost er empathy between consumers and riders, highlighting the challenges faced by delivery workers.\n\n\nYuanlinxi Li (Shenzhen International School of Design, Harbin Institute of Technology); Mengyao Guo (Shenzhen Internation al School of Design, Harbin Institute of Technology; University of Macau); and Ze Gao (Hong Kong University of Science and Technology)\n------------ ---------\nEmpowering CG Production：Cost-Effective Techniques for Volumino us Fur Rendering with Unreal Engine\n\nThis paper presents a comprehensive approach to rendering voluminous, realistic fur in Unreal Engine. We intr oduce strategies such as groom node-splitting, mesh conversion and density increase to optimize GPU memory usage and enhance rendering capacity.\n\n \nNing Xia, Xiaofei Yin, and Xuecong Feng (Children's Playground Entertain ment Inc.)\n---------------------\nEngaging Racing Fans through Offline E- racing Spectator Experience in AR\n\nA new spectator experience for engagi ng race fans on non-racing days. Spectators can watch an e-racer's virtual game car race against the pre-recorded car data from an actual race.\n\n\ nHsueh Han Wu (Rakuten Mobile, Inc.); Kelvin Cheng (Rakuten Institute of T echnology, Rakuten Group, Inc.; Rakuten Mobile, Inc.); and Jorge Luis Cháv ez Herrera and Koji Nishina (Rakuten Mobile, Inc.)\n---------------------\ nFast and Robust 3D Gaussian Splatting for Virtual Reality\n\nThe method p rovides fast and artifact-free rendering of 3D Gaussian Splatting scenes w ith user-grade VR hardware. We combine prior art and our own contributions to address popping, overly large Gaussians, and performance issues in VR settings to provide a smooth user experience, as confirmed by a sm...\n\n\ nXuechang Tu (Peking University, Carnegie Mellon University) and Bernhard Kerbl and Fernando de la Torre (Carnegie Mellon University)\n------------- --------\nFinger-Pointing Interface for Human Gesture Recognition Based on Real-Time Geometric Comprehension\n\nThis study introduces a interface us ing stereo cameras to recognize finger-pointing gestures and estimate 3D c oordinates, enhancing Human-Computer Interaction and intuitive user-robot communication. Future improvements target higher accuracy and reliability. \n\n\nMinjae Lee, Jiho Bae, Sang-Min Choi, and Suwon Lee (Gyeongsang Natio nal University)\n---------------------\nFitting Spherical Gaussians to Dyn amic HDRI Sequences\n\nWe present a technique for fitting high dynamic ran ge illumination (HDRI) sequences using anisotropic spherical Gaussians (AS Gs) while preserving temporal consistency in the compressed HDRI maps.\n\n \nPascal Clausen, Li Ma, Mingming He, Ahmet Levent Taşel, Oliver Pilarski, and Paul Debevec (Netflix Eyeline Studios)\n---------------------\nFluid Highlights: Stylized Highlights for Anime-Style Food Rendering by Fluid Si mulation\n\nWe propose a stylization method for highlights in anime-style rendering, mainly for food. We use fluid simulation to represent the highl ights of the squashed shapes that are unique to anime.\n\n\nAtsuki Haruyam a and Yuki Morimoto (Kyushu University)\n---------------------\nFlying You r Imagination: Integrating AI in VR for Kite Heritage\n\n``Flying Your Ima gination" is a project that integrates AI in VR for Kite Heritage; it inve stigates the innovative integration of VR, AI technology, and embodied int eraction design.\n\n\nKexin Nie (University of Sydney) and Mengyao Guo (Sh enzhen International School of Design, Harbin Institute of Technology; Uni versity of Macau)\n---------------------\nA Novel Projection Screen using the Crystalline Film of a Frozen Soap Bubble\n\nThis study proposes a nove l screen that focuses on the freezing phenomenon of soap films. Although s oap films are thin and transparent, in low-temperature environments, beaut iful ice crystals form on the surface, reducing transparency and enabling image projection onto the film. This study explores ...\n\n\nShinichiro Te rasawa, Oki Hasegawa, and Toshiki Sato (Japan Advanced Institute of Scienc e and Technology (JAIST))\n---------------------\nGaussians in the City: E nhancing 3D Scene Reconstruction under distractors with Text-guided Segmen tation and Inpainting\n\nA novel method for 3D scene reconstruction from i mages with both static and dynamic distractors captured in busy area. It u tilizes text-guided segmentation and inpainting for heavily masked regions .\n\n\nNaoki Shitanda and Jun Rekimoto (Sony CSL Kyoto, University of Toky o)\n---------------------\nGeneralizing Human Motion Style Transfer Method Based on Metadata-independent Learning\n\nThis study aims to extend the a pplicability of motion style transfer methods to be robust for diverse and complex motions akin to those found in real-world data.\n\n\nYuki Era, Re n Togo, Keisuke Maeda, Takahiro Ogawa, and Miki Haseyama (Hokkaido Univers ity)\n---------------------\nGenerating Font Variations Using Latent Space Trajectory\n\nVariable fonts can freely adjust the parameters of font pro perties and have been rapidly spreading recently.\n\nOur work will signifi cantly contribute to the further development of variable fonts.\n\n\nSotar o Kanazawa, I-Chao Shen, Yuki Tatsukawa, and Takeo Igarashi (University of Tokyo)\n---------------------\nGentlePoles : Designing Wooden Pole Actuat ors for Guiding People\n\nGentle Poles are wooden pole-like actuators that gently rotate to guide people without relying on text signs or staff. By arranging poles with individually controllable rotation direction and spee d, the system gently and subtly directs people. For example, changes in ro tation can convey messages suc...\n\n\nMasaya Shimizu, Berend te Linde, Ta katoshi Yoshida, Arata Horie, Nobuhisa Hanamitsu, and Kouta Minamizawa (Ke io University Graduate School of Media Design)\n---------------------\nGra dient Traversal: Accelerating Real-Time Rendering of Unstructured Volumetr ic Data\n\nNovel volume rendering algorithm for real-time rendering of uns tructured datasets. Two-pass approach with gradient estimation and gradien t traversal, leveraging modern GPGPU capabilities for interactive explorat ion of complex, dense volumetric data.\n\n\nMehmet Oguz Derin (Morgenrot, Inc.) and Takahiro Harada (Advanced Micro Devices, Inc.; Morgenrot, Inc.)\ n---------------------\nHeterogeneous Architecture for Asynchronous Seamle ss Image Stitching\n\nThis work proposes a seamless image stitching method on a heterogeneous CPU-GPU system that achieves 60fps at 4K resolution wi thout ghosting in real-time embedded environments.\n\n\nHyerin Cho, Jin-Wo o Kim, Jinhong Park, and Jeong-Ho Woo (VisioNexT)\n---------------------\n HidEye: Proposal of HMD Interaction Method by Hiding One Eye\n\nWe propose s HidEye, an interaction method that enables users to easily switch betwee n virtual and real space content by superimposing VR content with a pass-t hrough function triggered by covering one eye.\n\n\nRyunosuke Ise and Koji Tsukada (Future University Hakodate)\n---------------------\nHigh Spatial Resolution Projection Mapping for Visually Consistent Reproduction of Phy sical Surfaces\n\nIncreasing pixel density by optically reducing the proje ction area enables the presentation of a virtual object whose appearance p erceptually matches that of a real object with fine texture.\n\n\nIkuho Ta ni, Daisuke Iwai, and Kosuke Sato (Osaka University)\n-------------------- -\nHybrid Physical Model and Status Data-Driven Dynamic Control for Digita l Light Processing 3D Printing\n\nThis paper proposes a dynamic control sc heme for DLP 3D printing that combines physical models with status data. B y developing physical models, data capture, and analysis methods, we dynam ically adjust the printing protocol to improve efficiency.\n\n\nLidong Zha o and Xueyun Zhang (Beijing University of Technology), Lin Lu (Shandong Un iversity), and Lifang Wu (Beijing University of Technology)\n------------- --------\nIncremental Gaussian Splatting: Gradual 3D Reconstruction from a Monocular Camera Following Physical World Changes\n\nIncremental Gaussian Splatting enables real-time 3D reconstruction in dynamic environments usi ng a monocular camera. I-GS outperforms conventional methods, providing ac curate reconstructions resilient to moving objects, significantly enhancin g remote physical collaboration.\n\n\nKeigo Minamida (University of Tokyo) and Jun Rekimoto (University of Tokyo, Sony CSL Kyoto)\n----------------- ----\nIndividual Diffusion Auralize Display Using an Array of Audio Source Position Tracking Ultrasonic Speakers\n\nWe developed a prototype system called the "Individual Diffusion Auralize Display," which independently ge nerates each instrument’s sound using multiple parametric array loudspeake rs (PAL) and monitor speakers. The system adjusts the reflection points of the sounds based on the players’ ...\n\n\nHyuma Auchi, Akito Fukuda, Yuta Yamauchi, Homura Kawamura, and Keiichi Zempo (University of Tsukuba)\n--- ------------------\nIT3: Immersive Table Tennis Training Based on 3D Recon struction of Broadcast Video\n\nUsing 3D reconstruction and physical simul ation, we introduce a VR system for table tennis training that allows user s to refine their receiving skills and experience immersive game replays.\ n\n\nPei-Hsin Huang, Shang-Ching Liu, Li-Yang Huang, Chuan-Meng Chiu, Jo-C hien Wang, Pu Ching, and Hung-Kuo Chu (National Tsing Hua University) and Min-Chun Hu (National Tsing Hua University, Taiwan Institute of Sports Sci ence)\n---------------------\nJaku-in: A Cultural Skills Training System f or Recording and Reproducing Three-dimensional Body, Eye, and Hand Movemen ts\n\nWe propose "Jaku-in", which displays the expert’s hand movements and gazes in a three-dimensional reconstructed space using a point cloud to h elp the expert's intention for novices.\n\n\nSotaro YOKOI (SONY CSL Kyoto, University of Tokyo); Kaishi Amitani and Natsuki Hamanishi (SONY CSL Kyot o); and Jun Rekimoto (SONY CSL Kyoto, University of Tokyo)\n-------------- -------\nLandscape Cinemagraph Synthesis with Sketch Guidance\n\nWe propos ed a sketch-guided approach for generating landscape cinemagraphs from fre ehand sketches. The proposed approach can generate visually pleasing lands cape cinemagraphs from the provided structural and motion sketches.\n\n\nH ao Jin, Zhengyang Wang, Xusheng Du, Xiaoxuan Xie, and Haoran Xie (Japan Ad vanced Institute of Science and Technology (JAIST))\n--------------------- \nLatent Bias Correction in Outpainting Artworks\n\nThis paper describes r esearch on outpainting artworks. Our purpose is to eliminate unnecessary t endencies that frequently occur when outpainting an artwork, and we propos e a novel latent correction method.\n\n\nJung-Jae Yu and Dae-Young Song (E lectronics and Telecommunications Research Institute (ETRI))\n------------ ---------\nLi Bai the Youth: An LLM-Powered Virtual Agent for Children’s C hinese Poetry Education\n\nLi Bai the Youth is an interactive installation featuring a virtual agent powered by LLMs, offering real-time poetic dial ogue and enhancing children's engagement with cultural heritage through im mersive learning.\n\n\nYurun Chen, Xin Lyu, Tianzhao Li, and Zihan Gao (Co mmunication University of China)\n---------------------\nLocally Editing S teady Fluid Flow via Controlling Repulsive Forces from Terrain\n\nThis pap er presents a novel control method for steady fluid flows, such as rivers and waterfalls, simulated using SPH.\n\n\nYuki Kimura and Yoshinori Dobash i (Hokkaido University, Prometech CG Research) and Syuhei Sato (Hosei Univ ersity, Prometech CG Research)\n---------------------\nMambaPainter: Neura l Stroke-Based Rendering in a Single Step\n\nMambaPainter predicts a seque nce of parameterized brush strokes for stroke-based rendering. We achieved over 100 brush strokes in a single inference step based on the selective SSM layers, enabling the efficient translation of source images to the oil painting style.\n\n\nTomoya Sawada and Marie Katsurai (Doshisha Universit y)\n---------------------\nMaterial and Colored Illumination Separation fr om Single Real Image via Semi-Supervised Domain Adaptation\n\nWe propose a training strategy for intrinsic decomposition networks that bridges the d omain gap between synthetic and real images, enabling even simple CNN to a chieve excellent material and illumination separation.\n\n\nHao Sha, Tongt ai Cao, and Yue Liu (Engineering Research Center of Mixed Reality and Adva nced Display, School of Optics and Photonics, Beijing Institute of Technol ogy)\n---------------------\nMedia Bus: XR-Based Immersive Cultural Herita ge Tourism\n\nThis study introduces the Media Bus prototype for digital st orytelling in Seoul using XR, HMDs, and TOLEDs. It integrates VPS/GPS, AR, and TOLED displays, showing potential for enhancing urban tourism.\n\n\nJ ieon Du and Heewon Lee (Art Center Nabi), Jeongmin Lee (Deep.Fine), and Ge won Kim (Seoul Institute of the Arts)\n---------------------\nMixed Realit y Solutions for Tremor Disorders: Ergonomic Hand Motion and AR Rehabilitat ion\n\nIntroducing a mixed reality device for tremor disorders, combining ergonomic hand assistance with AR rehabilitation. It offers adaptive suppo rt, personalized exercises, and telehealth, enhancing motor control and us er autonomy.\n\n\nXinjun Li (Cornell University) and Zhenhong Lei (Rhode I sland School of Design)\n---------------------\nMMM: Mid-air image Moving in and out of the Mirror with backward glance in the mirror\n\nWe propose an optical system displaying mid-air images that move between the inside a nd outside of a mirror and presenting a worldview of the mirror as an adja cent virtual world.\n\n\nYasunori Akashi, Changyo Han, and Takeshi Naemura (University of Tokyo)\n---------------------\nMultidirectional Superimpos ed Projection for Delay-free Shadow Suppression on 3D Objects\n\nIntroduci ng our innovative multidirectional superimposed projection system designed to eliminate shadows on 3D objects without any delay. This breakthrough e nsures seamless user experiences, even with dynamic occlusions.\n\n\nTakah iro Okamoto, Daisuke Iwai, and Kosuke Sato (Osaka University)\n----------- ----------\nMultimodal Learning for Autoencoders\n\nWe propose Multimodal Autoencoder architecture and training scheme, in which images are reconstr ucted using both image and text inputs, rather than just images as its inp ut.\n\n\nWajahat Ali Khan and Seungkyu Lee (Kyung Hee University)\n------- --------------\nNatureBlendVR: A Hybrid Space Experience for Enhancing Emo tional Regulation and Cognitive Performance\n\nThe NatureBlendVR, interact ive experience designed to enhance emotional regulation and cognitive func tion by merging XR technology with bio-responsive physical elements.\n\n\n Kinga Skiers, Peng Danyang, and Giulia Barbareschi (Keio University Gradua te School of Media Design); Pai Yun Suen (Empathic Computing Lab, The Univ ersity of Auckland; Keio University Graduate School of Media Design); and Kouta Minamizawa (Keio University Graduate School of Media Design)\n------ ---------------\nNeural Clustering for Prefractured Mesh Generation in Rea l-time Object Destruction\n\nPrefracture method is a practical implementat ion for real-time object destruction that is hardly achievable within perf ormance constraints, but can produce unrealistic results due to its heuris tic nature. We approach the clustering of prefractured mesh generation as an unordered segmentation on poin...\n\n\nSeunghwan Kim, Sunha Park, and S eungkyu Lee (Kyung Hee University)\n---------------------\nNew Fashion: Pe rsonalized 3D Design with a Single Sketch Input\n\nIn this work, we democr atize 3D garment design using freehand sketches and a carefully designed t hree-stage conditional diffusion network with random sampling augmented po int cloud pre-training for high-quality 3D creation.\n\n\nTianrun Chen (Zh ejiang University); Xinyu Chen, Chaotao Ding, and Ling Bai (Huzhou Univers ity); Shangzhan Zhang (Zhejiang University); Lanyun Zhu (Singapore Univers ity of Technology and Design (SUTD)); Ying Zang and Wenjun Hu (Huzhou Univ ersity); and Zejian Li and Lingyun Sun (Zhejiang University)\n------------ ---------\nNot Just a Gimmick: A Preliminary Study on Designing Interactiv e Media Art to Empower Embedded Culture’s Practitioner\n\nThis paper focus es on cultural practitioners, explores new design approach for Interactive Media Art (IMA), and the potential of IMA to enhance traditional art crea tion and sustainability.\n\n\nYihao He (School of Arts and Media, Tongji U niversity)\n---------------------\nOut-Of-Core Diffraction for Terascale H olography\n\nDisplaying large-scale holograms with a wide field of view (F oV) requires ultra-high-resolution data, often reaching tera-scale sizes. We propose an out-of-core diffraction method that utilizes multiple SSDs s imultaneously to manage tera-scale holography within limited memory constr aints. To enhance...\n\n\nJaehong Lee and Duksu Kim (Korea University of T echnology and Education (KOREATECH))\n---------------------\nOverallNet: S cale-Arbitrary Lightweight SR Model for handling 360° Panoramic Images\n\n We propose a lightweight, scale-independent SR model incorporating various techniques named OverallNet. Further, we incorporate quantization to maxi mize efficiency during user inference, making it well-suited for processin g high-quality panoramics.\n\n\nDongSik Yoon, Jongeun Kim, Seonggeun Song, Yejin Lee, and Gunhee Lee (HDC LABS)\n---------------------\nPerceiving 3 D from a 2D Mid-air Image\n\nThis study examines depth perception in mid-a ir images. Participants compared images to real objects. Results show redu ced depth perception in mid-air images.\n\n\nSaki Kominato, Miyu Fukuoka, and Naoya Koizumi (University of Electro-Communications)\n---------------- -----\nPerceptually Uniform Hue Adjustment: Hue Distortion Cage\n\nA metho d for making perceptually linear hue adjustments leveraging the OKLab colo r space to shift colors in the L,a,b model rather than in L,c,h, as is com mon in other software.\n\n\nDeinyon Lachlan Davies and Chris Cook (Canva)\ n---------------------\nPhantom Audition: Using the Visualization of Elect romyography and Vocal Metrics as Tools in Singing Training\n\nOur approach aims to use EMG and vocal metrics to enhance vocal training with multi-mo dality feedback, comparing a professional singer and students to analyze m uscle control and quality.\n\n\nKanyu Chen (Keio University Graduate Schoo l of Media Design, Institute of Science Tokyo); Emiko Kamiyama (Keio Unive rsity Graduate School of Media Design); Ruiteng Li (Waseda University); Yi chen Peng and Daichi Saito (Institute of Science Tokyo); Erwin Wu (Institu te of Science Tokyo, Huawei); Hideki Koike (Institute of Science Tokyo); a nd Akira Kato (Keio University Graduate School of Media Design)\n--------- ------------\nPianoKeystroke-EMG: Piano Hand Muscle Electromyography Estim ation from Easily Accessible Piano Keystroke\n\nElectromyography is essent ial in skill acquisition despite its resource-intensive access. We focused on small hand muscle activities in piano performance and proposed an appr oach to estimate electromyography from cost-effective keystrokes.\n\n\nRuo fan Liu (Tokyo Institute of Technology, Sony Computer Science Laboratories ); Yichen Peng (Tokyo Institute of Technology); Takanori Oku (Shibaura Ins titute of Technology, NeuroPiano Institute); Erwin Wu (Huawei Japan, Tokyo Institute of Technology); Shinichi Furuya (Sony Computer Science Laborato ries); and Hideki Koike (Tokyo Institute of Technology)\n----------------- ----\nPnRInfo : Interactive Tactical Information Visualization for Pick an d Roll Event\n\nPnRInfo detects and visualizes pick-and-roll plays in 3D, enhancing basketball team performance through in-depth tactical analysis a nd interactive discussion.\n\n\nLI-HUAN SHEN and JOYCE SUN (International Bilingual School at Hsinchu Science Park) and JAN-YUE LIN, YI-HSUAN CHIU, SSU-HSUAN WU, TAI-CHEN TSAI, SHUN-HAN CHANG, HUNG-KUO CHU, and MIN-CHUN HU (National Tsing Hua University)\n---------------------\nReal-time Hologra phic Media System Utilizing HBM-based Holography Processor\n\nThis paper i ntroduces a real-time holographic media system that converts 2D or RGBD vi deos into 3D holograms. The core of this system includes a Linux host that extracts depth information from 2D images and transmits it via packets, a nd a holography processor leveraging high-bandwidth memory (HBM) t...\n\n\ nWonok Kwon, Sanghoon Cheon, Kihong Choi, and Keehoon Hong (Electronics an d Telecommunications Research Institute. Technology)\n-------------------- -\nReal-Time Transfer Function Editor for Direct Volume Rendering in Mixed Reality\n\nIntroducing an innovative MR system for Direct Volume Renderin g, enabling intuitive real-time transfer function customization with inter active node editing, color, and opacity controls for enhanced volumetric d ata visualization.\n\n\nJunseo Choi, Hyeonji Kim, Haill An, and Younhyun J ung (Gachon University)\n---------------------\nReborn of the White Bone D emon: Role-Playing Game Design Using Generative AI in XR\n\nThis paper pre sents "Reborn of the White Bone Demon," an XR RPG using GenAI for real-tim e storyline generation, enhancing player immersion and personalization thr ough AI-driven NPC interactions.\n\n\nXiaozhan Liang, Yu Wang, and Fengyi Yan (Beihang University); Zehong Ouyang and Yong Hu (Beihang University; S tate Key Laboratory of Virtual Reality Technology and Systems, Beihang Uni versity); and Siyu Luo (Tsinghua University)\n---------------------\nRethi nking motion keyframe extraction : a greedy procedural approach using a ne ural control rig\n\nCurrent keyframe extraction methods are unsuitable for 3D animators. Our novel approach, closer to their workflows, uses a neura l control-rig and an algorithm to optimize keyframe placement on MoCap ani mations.\n\n\nThéo Cheynel (Centre National de la Recherche Scientifique - Laboratoire d'informatique de l'École Polytechnique (LIX), Kinetix); Omar El Khalifi and Baptiste Bellot-Gurlet (Kinetix); and Damien Rohmer and Ma rie-Paule Cani (Centre National de la Recherche Scientifique - Laboratoire d'informatique de l'École Polytechnique (LIX))\n---------------------\nSe gmentation of 3D Gaussians using Masked Gradients\n\nA novel 3D segmentati on algorithm for Gaussian splatting that utilizes 2D masks and inference-t ime gradient backpropagation, significantly enhancing downstream applicati ons like AR, VR, 3DGS editing, asset generation, and more.\n\n\nJoji Josep h, Bharadwaj Amrutur, and Shalabh Bhatnagar (Indian Institute of Science)\ n---------------------\nSelf-attention Handwriting Generative Model\n\nThi s study introduces a GAN-based model, zi2zi self-attention, which incorpor ates residual blocks and Self-Attention Layers in the encoder and decoder. These enhancements capture handwriting font details, mimicking the writer ’s style.\n\n\nYu-Chiao Wang, Tung-Ju Hsieh, and Pei-Ying Chiang (National Taipei University of Technology)\n---------------------\nSemantics-guided 3D Indoor Scene Reconstruction from a Single RGB Image with Implicit Repr esentation\n\nWe enhance single-view 3D scene reconstruction by integratin g semantic segmentation with implicit functions, using a semantic-guided i mage encoder and categorical attention module, achieving improved feature extraction and reconstruction quality.\n\n\nYi-Ju Pan, Pei-Chun Tsai, and Kuan-Wen Chen (National Yang Ming Chiao Tung University)\n---------------- -----\nSensory Cravings: A Mixed Reality Installation Enhancing Psychologi cal Experiences through Multisensory Interactions\n\nSensory Cravings util izes mixed reality to create multisensory experiences simulating the emoti onal effects of consumables like coffee, alcohol, and desserts, aiming to alleviate stress and enhance well-being.\n\n\nShuyi Li, Yifan Ding, and Zi han Gao (Communication University of China)\n---------------------\nShadow s Being Vacuumed Away: An MR Experience of Shadow Loss of Body with Spine- Chilling and Body-Trembling, and Shadow Loss of Thing\n\nIn this MR exper ience, as your shadow is sucked into a vacuum cleaner, it simultaneously t riggers spine-chilling sensations and body vibrations. The shadows of obje cts are also drawn in.\n\n\nRyu Nakagawa, Kenta Hidaka, Shimpei Biwata, Sh o Kato, and Taiki Shigeno (Nagoya City University)\n---------------------\ nShortest Path Speed-up Through Binary Image Downsampling\n\nWe propose a novel approach to achieve huge speed-ups for shortest path computations on 2D binary images at the cost of slight inaccuracies through image downsam pling techniques.\n\n\nChia-Chia Chen and Chi-Han Peng (National Yang Ming Chiao Tung University)\n---------------------\nSignal2Hand: Sensor Modali ty Translation from Body-Worn Sensor Signals to Hand-Depth Images\n\nSigna l2Hand is a hand reconstruction method that directly reconstructs hand-dep th images from body-worn sensor signals.\n\n\nYuki Kubo (NTT Corporation) and Buntarou Shizuki (University of Tsukuba)\n---------------------\nSLAM- Based Illegal Parking Detection System\n\nThe paper proposes a SLAM-based system for real-time illegal parking detection, improving efficiency by ut ilizing unmanned patrol vehicles for automated enforcement in urban areas. \n\n\nJiho Bae, Minjae Lee, Ungsik Kim, and Suwon Lee (Gyeongsang National University)\n---------------------\nSound Signatures for Geometrical Shap es\n\nWe propose automatic generation of sound signatures—pseudowords whic h can be associated with certain features of geometric shapes such as roun dness, spikiness, etc.\n\n\nHanqin Wang and Alexei Sourin (Nanyang Technol ogical University (NTU))\n---------------------\nSpecTrack: Learned Multi- Rotation Tracking via Speckle Imaging\n\nSpecTrack uses a laser speckle-ba sed lensless camera to obtain multi-axis absolute rotations, doubling the accuracy of current rotation estimation techniques and enabling dynamic ro tation tracking with minimal hardware requirements.\n\n\nZiyang Chen (Univ ersity College London (UCL)), Mustafa Doğan (Adobe Research), Josef Spjut (NVIDIA), and Kaan Akşit (University College London (UCL))\n-------------- -------\nStrainer GAN: Filtering out Impurity Samples in GAN Training\n\nS trainer GAN: A method refining impure datasets to enhance GAN training. Us es automatic filtering to improve image quality and stability across vario us architectures. Effective for real-world applications with impure data.\ n\n\nJiho Shin and Seungkyu Lee (Kyunghee University)\n------------------- --\nStyle Transfer with Gesture Style Generator\n\nWe propose a new style transfer method with Gesture Style generator. It transfers style to the ou tput motion in the conventional style transfer manner while also incorpora ting generated Gesture Style.\n\n\nDaYeon Lee and Seungkyu Lee (Kyunghee U niversity)\n---------------------\nThermiapt: Sensory Perception of Quanti tative Thermodynamics Concepts in Education\n\nThis study introduces "Ther miapt," a multi-sensory device that enhances thermodynamic learning by int egrating visual and haptic experiences, significantly improving comprehens ion and retention through immersive interaction.\n\n\nAnji Fujiwara (Natio nal Institute of Technology, Nara College; Nara Institute of Science and T echnology (NAIST)) and Kodai Iwasaki, Tamami Watanabe, and Hideaki Uchiyam a (Nara Institute of Science and Technology (NAIST))\n-------------------- -\nTime Light: An Interface for Comparing National Treasure Murals Across Time\n\nTime Light is an interface for comparing damaged 2D artworks with their reconstructions. This study details its application using Takamatsuz uka Kofun murals as an example.\n\n\nWenze Song and Takefumi Hayashi (Kans ai University Graduate School of Informatics)\n---------------------\nTing le Tennis: Menstrual Experience Sensory Simulation Sport Device\n\nTingle Tennis, a menstrual period sensory simulation game, leverages VR technolog y and haptic feedback for an immersive experience highlighting the physica l and psychological challenges female athletes face during their periods.\ n\n\nShun-Han Chang (National Tsing Hua University); Chen-Chun Wu (Nationa l Tsing Hua University, National Chengchi University); Zi-Yun Lai, Tsung-Y en Lee, and Cheng-En Ho (National Tsing Hua University); and Min-Chun Hu ( National Tsing Hua University, Taiwan Institute of Sports Science)\n------ ---------------\nTowards Accelerating Physics Informed Graph Neural Networ k for Fluid Simulation\n\nWe introduce a pioneering Multi-GNN Processor Ph ysics-Informed Graph Neural Network (PIGNN) approach which reduced trainin g time of PIGNN to a quarter while maintaining the error rate.\n\n\nYidi W ang (NVIDIA, Singapore Institute of Technology); Frank Guan, Malcolm Yoke Hean Low, and Daniel Wang (Singapore Institute of Technology); and Aik Ben g Ng and Simon See (NVIDIA)\n---------------------\nTracery Designer: A Me taball-Based Interactive Design Tool for Gothic Ornaments\n\nThis study pr oposes a design support system for interactively designing Gothic ornament s. This system is capable of not only designing Gothic ornaments, but also generating shape-shifting animations of Gothic patterns.\n\n\nJoe Takayam a (Musashino Art University)\n---------------------\nTransparent 360-Degre e Display for High-Resolution Naked-Eye Stereoscopic Aerial Images\n\nThis study proposes a thin directional display that presents high-resolution s tereoscopic images floating in mid-air, viewable from all directions with a curved transparent reflector.\n\n\nMari Shiina and Naoki Hashimoto (Univ ersity of Electro-Communications)\n---------------------\nVibrotactile Inv isible Presence: Conveying Remote Presence through Moving Vibrotactile Foo tstep Cues on a Haptic Floor\n\nWe propose concept to convey presence by t ransmitting footsteps and vibrotactile cues from one space to another. Ou r prototype uses floor-mounted microphones to capture footsteps and underf loor transducers to create moving vibrations elsewhere. Preliminary experi ments showed that users can partiall...\n\n\nTakahiro Kusabuka, Yuichi Mak i, Kakagu Komazaki, Masafumi Suzuki, Hiroshi Chigira, and Takayoshi Mochiz uki (NTT Corporation)\n---------------------\nVisualization Methods for Ma nual Wheelchair Training: Impact on Communication Between Coaches and User s\n\nThis study evaluates a visualization method to enhance communication and skill improvement between wheelchair users and coaches, using video, p ose estimation, and sensor data during a 40-m sprint.\n\n\nXu Han (Tokyo M etropolitan University), Asuka Mano (Research Institute of National Rehabi litation Center for Persons with Disabilities), Saki Sakaguchi and Mina Sh ibasaki (Tokyo Metropolitan University), Tsuyoshi Nakayama (Research Insti tute of National Rehabilitation Center for Persons with Disabilities), Yuj i Higashi (Japanese Association of Occupational Therapists), and Kumiko Ku shiyama (Tokyo Metropolitan University)\n---------------------\nV-Wire: A Single-Wire System for Simplified Hardware Prototyping and Enhanced Fault Detection in Education\n\nWe introduce a V-Wire which can provide communic ation with power source for small sensor/display modules on one loop wire circuit, same as series connection of light bulbs.\n\n\nHideaki Nii (Keio University Graduate School of Media Design), Kazutoshi Kashimoto (Ristmik llc), and Shozaburo Shimada (VIVIWARE Japan Inc.)\n---------------------\n XR Avatar Prototype for Art Performance Supporting the Inclusion of Neurod iverse Artists\n\nOur prototype uses volumetric video and AR to create an interactive Noh performance, enabling neurodiverse artists and a Noh singe r to transcend cross-cultural and cross-ability barriers for inclusive art making.\n\n\nShigenori Mochizuki (College of Image Arts and Sciences, Rit sumeikan University); Jonathan Duckworth and Ross Eldridge (School of Desi gn, College of Design and Social Context, RMIT University); and James Hull ick (Jolt Sonic and Visual Arts Inc)\n\nRegistration Category: Enhanced Ac cess, Exhibit & Experience Access, Experience Hall Exhibitor, Full Access, Full Access Supporter, Trade Exhibitor END:VEVENT END:VCALENDAR