Authoring System for Choreography Using Dance Motion Retrieval and Synthesis

نویسندگان

  • Ryo Kakitsuka
  • Kosetsu Tsukuda
  • Satoru Fukayama
  • Naoya Iwamoto
  • Masataka Goto
  • Shigeo Morishima
چکیده

Dance animations of a three-dimensional (3D) character rendered with computer graphics (CG) have been created by using motion capture systems or 3DCG animation editing tools. Since these methods require skills and a large amount of work from the creator, automated choreography synthesis system has been developed to make dance motions much easier. However, those systems are not designed to reflect artists’ preferred context of choreography into the synthesized result. Therefore, supporting the user’s preference is still important. In this paper, we propose a novel dance creation system that supports the user to create choreography with their preferences. A user firstly selects a preferred motion from the database, and then assigns it to an arbitrary section of the music. With a few mouse clicks, our system helps a user to search for alternative dance motion that reflects his or her preference by using relevance feedback. The system automatically synthesizes a continuous choreography with the constraint condition that the motions specified by the user are fixed. We conduct user studies and show that users can create new dance motions easily with their preferences by using the system.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

ChoreoGraphics: An Authoring Tool for Dance Shows

This work describes a computer system for authoring dance shows. The system can be used both as a mechanism to synthesize virtual group performances and as a tool for interactive design and visualization of real choreographies. To this end, we use as input motion capture of dance sequences that are synchronized with an underlying musical composition. We adapt motion synthesis methods for use in...

متن کامل

Automated Motion Synthesis for Virtual Choreography

In this paper, we present a technique to automatically synthesize dancing moves for arbitrary songs. Our current implementation is for virtual characters, but it is easy to use the same algorithms for entertainer robots, such as robotic dancers. Our technique is based on analyzing a musical tune (can be a song or melody) and synthesizing a motion for the virtual character where the character's ...

متن کامل

Generative Choreography using Deep Learning

Recent advances in deep learning have enabled the extraction of high-level features from raw sensor data which has opened up new possibilities in many different fields, including computer generated choreography. In this paper we present a system chorrnn for generating novel choreographic material in the nuanced choreographic language and style of an individual choreographer. It also shows promi...

متن کامل

Towards Multimodal Capture, Annotation and Semantic Retrieval from Performing Arts

A well-annotated dance media is an essential part of a nation’s identity, transcending cultural and language barriers. Many dance video archives suffer from tremendous problems concerning authoring and access, because of the multimodal nature of human communication and complex spatio-temporal relationships that exist between dancers. A multimodal dance document consists of video of dancers in s...

متن کامل

Expressive Trajectories

This paper presents Expressive Trajectories, a project for Interactive Digital Art and Contemporary Dance. The project has two main components: X-Motion, a real-time interactive system for live performances; and Choreographisms, an interface abstraction for graphical interpretation of motion-paths. This framework is demonstrated through an experiment that includes a choreography of the artist–c...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017