研究発表

Smart Ambient Media (SAM) is a display methodology designed to seamlessly enhance various daily activities by utilizing a real-time human-in-the-loop framework that integrates multimodal sensing, intelligent computation, and adaptive rendering. This keynote will provide an overview of the fundamental principles of SAM, followed by three key applications: 1) Ambient Music co-Player (AMP)—a system that captures real-time performance data from an improvising electric guitar soloist and dynamically generates corresponding visuals to interact with the player. 2) Computational ophthalmology—Computational glasses provide visual impaired individuals with the same amount of visual information as perceived by sighted ones depending on the kind of visual dysfunction. 3) Anamorphosis-based stereoscopic viewer (ANSWER)—a simple, glasses-free stereoscopic display utilizing an orthogonally arranged pair of monitors, where motion parallax effects are induced through eye-tracking and the visual perception of a cyclopean eye.

Leading lines are a cornerstone of artistic composition, subtly directing an observer's gaze to enhance both understanding and aesthetic experience. Yet, recognizing these lines can pose challenges, particularly for those without formal training in art or photography. While saliency maps have been widely used to identify prominent regions in visual content, their conventional scalar representations fail to capture the dynamic flow of visual attention. To address this, we present a visual analysis system that combines discrete Morse theory with refined saliency maps utilizing persistent homology. By transforming gradient fields into structured maximum graphs—streamlined subsets of Morse–Smale complexes—our system identifies both explicit and implicit leading lines in paintings and photographs. In addition, texture gradient cues are integrated to introduce depth perception, accounting for spatial hierarchies in visual compositions. Advanced features, including semiautomatic thresholding via the elbow method and tools for visualizing the directional flow of gaze, offer a dynamic and efficient approach to understanding visual guidance. An experimental validation was conducted at Joshibi University of Art and Design, Tokyo, analyzing Western artworks from the 17th to 19th centuries, including Baroque, Rococo, Romanticism, and Impressionist styles. Comparisons between system outputs, manually drawn leading lines, together with eye-tracking data demonstrated remarkable alignment, underscoring the system’s effectiveness. Participants praised the system’s usability and interactive graphical representation, though refinements such as customizable thresholding processes remain a promising avenue for future improvements. This was invited by Symposium on Connoisseurship to Computation; Rethinking the role of visual analysis in the study of art and its perception.

新たなプログラミングモデルであるGPU work graphを用いて，等値面抽出に使われるマーチングキューブ法の適応的高速化に関する方法について初期的検討を行った．

Join us as we bridge the gap between academia and industry, sharing insights, strategies, and best practices to enhance the educational experience. Whether you’re a seasoned educator, a passionate researcher, or an industry professional looking to make a difference, there’s something for everyone at the Educator’s Forum. At SIGGRAPH Asia, education isn’t just about classrooms and textbooks—it’s about sparking curiosity, fostering creativity, and empowering minds to push the boundaries of what’s possible. Our forum is a dynamic melting pot of ideas, where educators from academia and industry come together to share innovative research, methodologies, and developments that are shaping the future of learning. As we delve into this year’s theme of “Curious Minds,” we invite you to join the conversation and discover how education plays a pivotal role in connecting stories across diverse communities and disciplines. From immersive workshops to captivating talks and interactive sessions, the Educator’s Forum promises a wealth of insights and inspiration for educators and learners alike.

川崎市立日本民家園に収蔵されている屋根鋏への適用例を中心に，XRによる民具の操作の第一人称的体験の意義について説明する．

川崎市立日本民家園に収蔵されている屋根鋏や唐箕への適用例を中心に，XRによる民具の操作の第一人称的体験の意義について説明する．

ACM SIGGRAPH 2023参加報告．過去50年間のCG技術の変遷を概観した．

ラボで展開しているスマートアンビエントメディアの概念を説明し，その代表的事例である，即興演奏支援，裸眼立体視，計算眼鏡の3件のプロジェクトの成果を説明した．

Inspired by the trick artworks of a young Japanese artist Hideyuki Nagai, we developed a simple, naked-eye stereoscopic viewer for personal use. The system is equipped only with the orthogonal arrangement of two general-purpose display monitors together with a web camera and induces motion parallax by tracking the viewer’s eyes to update the state of anamorphosis, known as monocular illusion expression. The stereoscopic effect perceived by the user may be degraded due to binocular disparity, especially when the viewer is used with small display monitors. It has been empirically proven that the sense of presence can be improved by placing a so-called Cyclopean eye at a specific position on the line between the two eyes to obtain a pinpointed anamorphosis. The viewer, however, encounters a problem that displayed objects may be either partially beyond the rendering area or completely missing, depending on the object’s position relative to the user’s viewpoint, resulting in a reduced stereoscopic effect. We attempt to address this problem by employing a so-called frame-break method that has recently been used in filmmaking and advertisement. I also report on a trial porting of the viewer to a commercially available laptop PC with a foldable display.

深層学習を利用したコンピュータグラフィックスの世界に招待します．三次元復元した貴重な文化財のバーチャル操作を可能にしたり，動画の世界観を一枚の静止画で可視化したりするシステム等を紹介します．

第6回羽倉賞（藤代），第7回羽倉賞優秀賞（久保）を受賞した裸眼立体映像生成とインダイレクトビジョン技術を紹介する特別講演．

CGI2023で発表した同名の論文を，国際招待セッションで発表．

新学術領域「疎成モデリング」の計画研究C01-3（可視化班）のその後の展開について，天文学視覚解析システムTimeTubesXを中心に紹介した．

加法的重み付きボロノイ分割を中心に，オパールのビジュアルシミュレーションの高度化に資する要素技術の取り込みについて紹介した．

異種メディア変換の例として新たにビデオからヴィネットイラストを半自動的に生成する問題を採り上げ，背景と目的，ヴィネットイラストの五大要素，プロトタイピングの仕組みについて説明した．

Inspired by the trick artworks of young Japanese artist Hideyuki Nagai, we developed a simple, naked-eye stereoscopic viewing system for personal use. The system is equipped only with the orthogonal arrangement of two general-purpose display monitors together with a web camera and induces motion parallax by tracking the viewer’s eyes to update the state of anamorphosis, known as monocular illusion expression. The stereoscopic effect perceived by the viewer may be degraded due to binocular disparity, especially when the system is being used with small display monitors. It has been empirically proven that the sense of presence can be improved by placing a so-called Cyclopean eye at a specific position on the line between the two eyes to obtain pinpointed anamorphosis. The system, however, experiences a problem wherein displayed objects may be either partially beyond the rendering area or completely missing, depending on the object’s position relative to the user’s viewpoint, resulting in a reduced stereoscopic effect. We attempt to address this problem by employing a so-called frame break method that has recently been used in filmmaking and advertisement. I report on a trial porting of the system to a commercially available laptop PC with a foldable display.

画面をのぞき込むのではなく，物体が画面から飛び出すように見えたら？裸眼立体視は誰をも魅了する技術です．この講義では，高価なデバイスを使わなくても，アナモルフォーシス（歪像）に，影付けと視線追跡を組み合わせることによって運動視差を誘発し，折畳み可能ディスプレイが搭載されたモバイル機器でも単眼性の裸眼立体視が実現できることを証明します．この仕組みから得られる立体視をよりシャープにするために，サイクロープスの眼という概念の利用にもふれます．