各位同学、老师：你们好！
学院很高兴地邀请到我们浙大校友、博世美国研究中心研究员、任骝博士，于本周二在CAD&CG国家重点实验室（紫金港校区）作学术报告。
报告题目：Generating Natural Human Motion
报告时间：11月20 日(周二)下午2:00---3:00
报告地点：CAD&CG国家重点实验室（紫金港校区）402会议室 。
在报告结束之后，我们还将安排任骝博士和广大师生进行座谈交流，畅谈在美国卡内基梅隆大学的一流的学术环境、研究机制，以及如何开展有意义的研究项目。
座谈时间：11月20 日(周二)下午3:30---4:30
座谈地点：CAD&CG国家重点实验室（紫金港校区）402会议室 。
欢迎广大师生积极参加，并请转告其他感兴趣的师生参加，谢谢！
以下是关于任骝博士的简要介绍和学术报告的摘要：
Short Bio: Dr. Liu Ren is currently a graphics research scientist in Bosch Research and Technology Center at Palo Alto, California. He received his Ph.D. in Computer Science from Carnegie Mellon University in 2006, with research focused on data-driven methods, character animation and real-time rendering. He received the B.S. and M.S. degree from Department of Computer Science at Zhejiang University in 1996 and 1999.
Title: Generating Natural Human Motion
Abstract: Generating human motion that appears natural is a long standing problem in character animation. There are two major reasons why this is a very difficult problem. First, as natural human motion has many degrees of freedom, intuitive motion control or motion generation is very challenging by nature. Second, like many other problems in computer graphics, we are lack of an implementable definition of what it means for motion to be natural or human-like for character animation.
In this talk, I will present two pieces of my research work to address these issues. First, I will introduce a vision-based performance interface ("do as I do" interface) for controlling the full-body motion of animated human characters. The interface is intuitive, low cost and non-intrusive. It combines information about the user's motion contained in silhouettes from three viewpoints with domain knowledge contained in a motion capture database to interactively produce a high quality animation. Such an interactive system will be useful for authoring, for teleconferencing, or as a control interface for a character in a game. To address the second issue, I will present a naturalness measure for quantifying natural human motion. Such a naturalness measure should be useful in verifying that a motion editing operation has not destroyed the naturalness of a motion capture clip or that a synthetic motion transition is within the space of those seen in natural human motion. To develop such a measure, we argue that the evaluation of naturalness is not intrinsically a subjective criterion imposed by a human observer but rather, an objective measure that can be computed from a large set of representative motion.
The technical content of this talk will be based on the research work done at CMU. As CMU graphics group are leading the research for character animation in the world, I will also share the experience on how we chose good research topics. In the end of talk, I will briefly talk about research activities at Bosch Research and Technology Center in Palo Alto, CA and introduce our internship or visiting student/scholar program.
学院很高兴地邀请到我们浙大校友、博世美国研究中心研究员、任骝博士，于本周二在CAD&CG国家重点实验室（紫金港校区）作学术报告。
报告题目：Generating Natural Human Motion
报告时间：11月20 日(周二)下午2:00---3:00
报告地点：CAD&CG国家重点实验室（紫金港校区）402会议室 。
在报告结束之后，我们还将安排任骝博士和广大师生进行座谈交流，畅谈在美国卡内基梅隆大学的一流的学术环境、研究机制，以及如何开展有意义的研究项目。
座谈时间：11月20 日(周二)下午3:30---4:30
座谈地点：CAD&CG国家重点实验室（紫金港校区）402会议室 。
欢迎广大师生积极参加，并请转告其他感兴趣的师生参加，谢谢！
以下是关于任骝博士的简要介绍和学术报告的摘要：
Short Bio: Dr. Liu Ren is currently a graphics research scientist in Bosch Research and Technology Center at Palo Alto, California. He received his Ph.D. in Computer Science from Carnegie Mellon University in 2006, with research focused on data-driven methods, character animation and real-time rendering. He received the B.S. and M.S. degree from Department of Computer Science at Zhejiang University in 1996 and 1999.
Title: Generating Natural Human Motion
Abstract: Generating human motion that appears natural is a long standing problem in character animation. There are two major reasons why this is a very difficult problem. First, as natural human motion has many degrees of freedom, intuitive motion control or motion generation is very challenging by nature. Second, like many other problems in computer graphics, we are lack of an implementable definition of what it means for motion to be natural or human-like for character animation.
In this talk, I will present two pieces of my research work to address these issues. First, I will introduce a vision-based performance interface ("do as I do" interface) for controlling the full-body motion of animated human characters. The interface is intuitive, low cost and non-intrusive. It combines information about the user's motion contained in silhouettes from three viewpoints with domain knowledge contained in a motion capture database to interactively produce a high quality animation. Such an interactive system will be useful for authoring, for teleconferencing, or as a control interface for a character in a game. To address the second issue, I will present a naturalness measure for quantifying natural human motion. Such a naturalness measure should be useful in verifying that a motion editing operation has not destroyed the naturalness of a motion capture clip or that a synthetic motion transition is within the space of those seen in natural human motion. To develop such a measure, we argue that the evaluation of naturalness is not intrinsically a subjective criterion imposed by a human observer but rather, an objective measure that can be computed from a large set of representative motion.
The technical content of this talk will be based on the research work done at CMU. As CMU graphics group are leading the research for character animation in the world, I will also share the experience on how we chose good research topics. In the end of talk, I will briefly talk about research activities at Bosch Research and Technology Center in Palo Alto, CA and introduce our internship or visiting student/scholar program.
