詳細資料
|
07/21(二)邀請黃田津教授來系演講
各位老師、同學： 系上李同益老師邀請 The Chinese University of Hong Kong的黃田津教授至系上演講，檢附詳細資訊及時間地點於文後，機會難得，請大家踴躍參加！ 日 期：07月21日(二) 內容摘要： Even though the temporal information is lost, a still picture of moving animals hints at their motion. In this paper, we infer motion cycle of animals from the "motion snapshots" (snapshots of different individuals) captured in a still picture. By finding the motion path in the graph connecting motion snapshots, we can infer the order of motion snapshots with respect to time, and hence the motion cycle. Both "half-cycle" and "full-cycle" motions can be inferred in a unified manner. Therefore, we can animate a still picture of a moving animal group by morphing among the ordered snapshots. By refining the pose, morphology, and appearance consistencies, smooth and realistic animal motion can be synthesized. Our results demonstrate the applicability of the proposed method to a wide range of species, including birds, fishes, mammals, and reptiles. 個人簡介： Professor WONG, Tien-Tsin (T. T.) (黃田津) is currently a professor. He is a core member of Virtual Reality, Visualization and Imaging Research Centre in the Chinese University of Hong Kong. Recently, he received the IEEE Transactions on Multimedia Prize Paper Award 2005 and the Young Researcher Award 2004. He was a visiting researcher in Microsoft Research, Asia during the summer of 2000. Currently, he is also a visiting research professor in Biomedical Engineering Department of Shanghai Jiaotong University. He is the member of ACM, ACM SIGGRAPH, IEEE, and Eurographics Association. He has actively involved (as Program Co-chair, Program Committee and Organizing Committee) in several international conferences, including Eurographics (2007), Pacific Graphics (2000-2005), Computer Graphics International (2004, 2006), Medical Imaging and Augmented Reality (2001), International Conference on Image and Graphics (2002), CAD/Graphics (2003, 2005, 2006), Chinagraph (2000, 2002, 2004, 2006) and ACM VRCIA (2006). Besides, he is also active in transferring graphics technologies to games industry, including writing articles in books for game developers (Graphics Gems V, Graphics Programming Methods, Shader X3, ShaderX4, and ShaderX5). His main research interests include computer graphics, precomputed lighting, image-based rendering, non-photorealistic rendering (manga), GPU programming, medical visualization, multimedia compression, and computer vision. In 1997, he proposed one of the earliest representations for image-based relighting, apparent BRDF of pixel. He also proposed a geometry-dependent framework for modeling surface imperfections, such as dust accumulation, in 1995 (reported in Computer Graphics World magazine). Currently, he actively involves in the projects of Rendering-friendly Compression and Real-Time Visualization of Chinese Visible Human (see press clipping), the highest resolution visible human data set. Click [favorite] to see his favorite research papers he published in SIGGRAPH and other venues.
相關網址：無 |