GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models
This paper introduces a GPU (graphics processing unit)-based fast motion synthesis algorithm for a large crowd. The main parts of the algorithms were selecting the most appropriate joint model given adaptive screen-space occupancy of each character and synthesizing motions for the joint model with o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/3/422 |
| _version_ | 1818039091888914432 |
|---|---|
| author | Mankyu Sung Yejin Kim |
| author_facet | Mankyu Sung Yejin Kim |
| author_sort | Mankyu Sung |
| collection | DOAJ |
| description | This paper introduces a GPU (graphics processing unit)-based fast motion synthesis algorithm for a large crowd. The main parts of the algorithms were selecting the most appropriate joint model given adaptive screen-space occupancy of each character and synthesizing motions for the joint model with one or two input motion capture data. The different joint models had a character range from fine-detailed and fully-articulated ones to the most simplified ones. The motion synthesizer, running on a GPU, performed a series of motion blending for each joint of the characters in parallel. For better performance of the motion synthesizer, the GPU maintained a novel cache structure for given speed parameters. Using the high computation power of GPUs, the motion synthesizer could generate arbitrary speeds and orientations for the motions of a vast number of characters. Experiments showed that the proposed algorithm could animate more than 5000 characters in real-time on modest graphics acceleration cards. |
| first_indexed | 2024-12-10T07:53:08Z |
| format | Article |
| id | doaj.art-e5bf20e2006448af99ea643603e4d073 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-12-10T07:53:08Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-e5bf20e2006448af99ea643603e4d0732022-12-22T01:56:58ZengMDPI AGSymmetry2073-89942019-03-0111342210.3390/sym11030422sym11030422GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint ModelsMankyu Sung0Yejin Kim1Department of Game and Mobile, Keimyung University, Daegu 42601, KoreaSchool of Games, Hongik University, Sejong 30016, KoreaThis paper introduces a GPU (graphics processing unit)-based fast motion synthesis algorithm for a large crowd. The main parts of the algorithms were selecting the most appropriate joint model given adaptive screen-space occupancy of each character and synthesizing motions for the joint model with one or two input motion capture data. The different joint models had a character range from fine-detailed and fully-articulated ones to the most simplified ones. The motion synthesizer, running on a GPU, performed a series of motion blending for each joint of the characters in parallel. For better performance of the motion synthesizer, the GPU maintained a novel cache structure for given speed parameters. Using the high computation power of GPUs, the motion synthesizer could generate arbitrary speeds and orientations for the motions of a vast number of characters. Experiments showed that the proposed algorithm could animate more than 5000 characters in real-time on modest graphics acceleration cards.https://www.mdpi.com/2073-8994/11/3/422crowd simulationmotion synthesismulti-joints modelcharacter animationGPU acceleration |
| spellingShingle | Mankyu Sung Yejin Kim GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models Symmetry crowd simulation motion synthesis multi-joints model character animation GPU acceleration |
| title | GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models |
| title_full | GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models |
| title_fullStr | GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models |
| title_full_unstemmed | GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models |
| title_short | GPU-based Fast Motion Synthesis of Large Crowds Using Adaptive Multi-Joint Models |
| title_sort | gpu based fast motion synthesis of large crowds using adaptive multi joint models |
| topic | crowd simulation motion synthesis multi-joints model character animation GPU acceleration |
| url | https://www.mdpi.com/2073-8994/11/3/422 |
| work_keys_str_mv | AT mankyusung gpubasedfastmotionsynthesisoflargecrowdsusingadaptivemultijointmodels AT yejinkim gpubasedfastmotionsynthesisoflargecrowdsusingadaptivemultijointmodels |