지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- Korean Institute of Information Scientists and Engineers Journal of Computing Science and Engineering Journal of Computing Science and Engineering Vol.18 No.4
- 발행연도
- 2024.12
- 수록면
- 181 - 195 (15page)
- DOI
- 10.5626/JCSE.2024.18.4.181
이용수
초록· 키워드
오류제보하기
We investigate a motion generation model capable of producing desired motions using minimal pose data. Although similar to conventional motion interpolation models in terms of motion data input, the key difference lies in our model's ability to generate diverse motions tailored to user intentions. To differentiate it from motion interpolation models, we establish motion recognition and controllable motion generation systems utilizing pretrained generative models. We develop the motion recognition system using a latent vector derived from the pretrained model's encoder, which encodes substantial contextual information and can be identified by a simple linear support vector machine. The controllable motion generation system employs the recognized latent vector and input poses, based on the pretrained model's decoder. In experiments, our model demonstrates superior generated motion accuracy compared to text-based motion generation models. We also compare our model with motion interpolation models, showing comparable performance. Furthermore, we validate the efficacy of skip connections through qualitative evaluations. Finally, we confirm that our system can gen- erate various types of motion utilizing latent vectors.
목차
Abstract
I. INTRODUCTION
II. RELATED WORK
III. PROPOSED SYSTEM
IV. EXPERIMENTS
V. CONCLUSION
REFERENCES
참고문헌 (52)
참고문헌 신청
F. Hong, M. Zhang, L. Pan, Z. Cai, L. Yang, and Z. Liu, “AvatarCLIP: zero-shot text-driven generation and animation of 3D avatars,” 2022 [Online]. Available: https://arxiv.org/abs/2205.08535.
G. Xia, P. Xue, D. Zhang, and Q. Liu, “Keyframe-editable real-time motion synthesis,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 7, pp. 4538-4551, 2022. https://doi.org/10.1109/TCSVT.2021.3129478
M. Petrovich, M. J. Black, and G. Varol, “Action-conditioned 3D human motion synthesis with transformer VAE,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021, pp. 10965-10975. https://doi.org/10.1109/ICCV48922.2021.01080
T. Lucas, F. Baradel, P. Weinzaepfel, and G. Rogez, “PoseGPT:Quantization-based 3d human motion generation and forecasting,”in Computer Vision – ECCV 2022. Cham, Switzerland: Springer,2022, pp. 417-435. https://doi.org/10.1007/978-3-031-20068-7_24
C. Guo, X. Zuo, S. Wang, S. Zou, Q. Sun, A. Deng, M. Gong, and L. Cheng, “Action2motion: conditioned generation of 3D human motions,” in Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA, 2020, pp.2021-2029. https://doi.org/10.1145/3394171.3413635
G. Xia, P. Xue, D. Zhang, and Q. Liu, “Keyframe-editable real-time motion synthesis,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 7, pp. 4538-4551, 2022. https://doi.org/10.1109/TCSVT.2021.3129478
M. Petrovich, M. J. Black, and G. Varol, “Action-conditioned 3D human motion synthesis with transformer VAE,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021, pp. 10965-10975. https://doi.org/10.1109/ICCV48922.2021.01080
T. Lucas, F. Baradel, P. Weinzaepfel, and G. Rogez, “PoseGPT:Quantization-based 3d human motion generation and forecasting,”in Computer Vision – ECCV 2022. Cham, Switzerland: Springer,2022, pp. 417-435. https://doi.org/10.1007/978-3-031-20068-7_24
C. Guo, X. Zuo, S. Wang, S. Zou, Q. Sun, A. Deng, M. Gong, and L. Cheng, “Action2motion: conditioned generation of 3D human motions,” in Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA, 2020, pp.2021-2029. https://doi.org/10.1145/3394171.3413635
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
음악과 모션 데이터 분석을 이용한 로봇의 춤동작 생성
한국정밀공학회 학술발표대회 논문집
2019 .10
-
Signaling Method of Multiple Motion Vector Resolutions Using Contradiction Testing
전자공학회논문지
2015 .07
-
A Novel Frame rate Conversion Method by Using Improved True Motion Estimation
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
-
Image reconstruction technique using deep learning architecture
Journal of Advanced Marine Engineering and Technology (JAMET)
2018 .02
-
공연자의 실영상 기반 캐릭터 동작 생성 기술 개발
한국정밀공학회 학술발표대회 논문집
2022 .05
-
A Consecutive Motion and Situation Recognition Mechanism to Detect a Vulnerable Condition Based on Android Smartphone
International JOURNAL OF CONTENTS
2020 .09
-
동작인식 기술을 적용한 운동능력 측정 시스템 개발
대한전자공학회 학술대회
2020 .08
-
A study on rotational motion control for ship steering motion control
Journal of Advanced Marine Engineering and Technology (JAMET)
2016 .02
-
Motion Field Estimation Using U-Disparity Map in Vehicle Environment
Journal of Electrical Engineering & Technology
2017 .01
-
모션 벡터의 각도 성분 추정을 통한 카메라 움직임 검출
멀티미디어학회논문지
2018 .09
-
차량 운전 시뮬레이터에서 모션과 영상의 동기화를 위한 알고리즘 및 구현 방안
로봇학회 논문지
2017 .06
-
Sensed Unit Motion based Authoring for the Precise Human Movements
대한기계학회 춘추학술대회
2020 .12
-
Motion Vector Estimation for Transparent Sequences
대한기계학회 춘추학술대회
2015 .04
-
동작인식 기술을 적용한 운동능력 측정 기술과 시스템 개발
대한전자공학회 학술대회
2020 .11
-
Realization of a hybrid human motion capture system
제어로봇시스템학회 국제학술대회 논문집
2017 .10
-
Survey on Time-Series Human Motion Information Processing using Machine Learning Approach
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2018 .06
-
운동축척을 이용한 모션 깊이맵 생성
한국방송미디어공학회 학술발표대회 논문집
2016 .11
-
HEVC에서의 Motion Vector Difference 부호화에 관한 연구
대한전자공학회 학술대회
2016 .06
-
Modelling of Bio-Inspired Silicon Retina for self-motion, object motion and looming detection
한국정보통신학회 종합학술대회 논문집
2024 .10
-
학습기법을 이용한 로봇의 모션패턴 생성 연구
JOURNAL OF PLATFORM TECHNOLOGY
2018 .09
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-25-02-092300769