무게중심을 활용한 모션 생성 기술
Motion generation using Center of Mass
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
캐릭터의 자세가 변할 때 마다 캐릭터의 무게 중심(COM) 위치도 변하게 된다. 이 때 무게 중심의 위치 변화는 걷기, 뛰기, 쭈그려 앉기 등 다양한 동작 각각에 대응되는 독자적인 패턴을 가지므로 이를 이용하면 원래 동작의 정보를 알아낼 수 있다. 본논문에서는캐릭터의무게중심의위치변화를토대로동작을예측하는모션생성기법을제안한다.이방법을이용하면무게중심 정보를 통해 원래 동작의 유형에 대한 별도의 label 없이도 다양한 동작을 생성할 수 있다. 그러므로 네트워크의 학습 및실행을 위한 데이터셋을 만들 때 사람의 손을 거칠 필요 없이 전처리를 비롯한 모든 과정을 자동으로 진행할 수 있다. 본 논문에서 제안하는 신경망 모델은 캐릭터의 모션 history 정보와 무게 중심 정보들을 입력 받아 현재 프레임에서의 포즈 정보를출력하며, 연속적인 시계열 모션 데이터를 다루기 위해 1D Convolution을 수행하는 Convolutional Neural Network(CNN)를사용하여 학습되었다. 이 모델을 통해 캐릭터의 동작을 만드는데 무게 중심 정보를 활용하는 것이 유용하다는 것을 보인다.
Abstract
When a character’s pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion type like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character’s center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generate a full-body pose for the current frame, and is trained using Convolutional Neural Network(CNN) performs 1D convolution to deal with time-series motion data. We demonstrate the usefulness of using center of mass information for generating character motions using our method.
참고문헌 (22)
- D. Holden, "Learning motion manifolds with convolutional autoencoders", SIGGRAPH Asia 2015 Technical Briefs, pp.1~4 (2015)
- I. Mordatch, "Interactive control of diverse complex characters with neural networks", Advances in Neural Information Processing Systems, pp.3132~3140 (2015)
- D. Holden, "Phase-functioned neural networks for character control", ACM Transactions on Graphics(TOG), 36(4), pp.1~13 (2017)
- H. Zhang, "Mode-adaptive neural networks for quadruped motion control", ACM Transactions on Graphics(TOG), 37(4), pp.1~11 (2018)
- J. Lee, "Interactive control of avatars animated with human motion data", Proceedings of the 29th annual conference on Computer graphics and interactive techniques, pp.491~500 (2002)
- L. Kovar, "Motion graphs", Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, ser. SIGGRAPH ’02, pp.473~482 (2002), Association for Computing Machinery
- O. Arikan, "Interactive motion generation from examples", ACM Transactions on Graphics(TOG), 21(3), pp.483~490 (2002)
- M. Lau, "Behavior planning for character animation", Proceedings of the 2005 ACM SIGGRAPH, 2005, 271~280
- K. Hyun, "Motion grammars for character animation", Computer Graphics Forum, 35(2), pp.103~113 (2016), Wiley Online Library
- E. Hsu, "Style translation for human ´motion", ACM SIGGRAPH 2005 Papers, pp.1082~1089 (2005)
- Y. Lee, "Motion fields for interactive character locomotion", ACM SIGGRAPH Asia 2010 papers, pp.1~8 (2010)
- J. M. Wang, "Gaussian process dynamical models for human motion", IEEE transactions on pattern analysis and machine intelligence, 30(2), pp.283~298 (2007)
- G. W. Taylor, "Factored conditional restricted boltzmann machines for modeling motion style", Proceedings of the 26th Annual International Conference on Machine Learning, ser. ICML ’09, pp.1025~1032 (2009), Association for Computing Machinery
- G. W. Taylor, "Two distributed-state models for generating high-dimensional time series", Journal of Machine Learning Research, 12, pp.1025~1068 (2011)
- K. Lee, "Interactive character animation by learning multi-objective control", ACM Transactions on Graphics(TOG), 37(6), pp.1~10 (2018)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in neural information processing systems, pp.1097~1105 (2012)
- O. Abdel-Hamid, "Convolutional neural networks for speech recognition", IEEE, 2014, pp.22(10), 1533~1545
- V. Nair, "Rectified linear units improve restricted boltzmann machines", Proceedings of the 27th international conference on machine learning (ICML-10), pp.807~814 (2010)
- J. Chai, "Performance animation from lowdimensional control signals", ACM SIGGRAPH 2005 Papers, pp.686~696 (2005)
- J. Min, "Motion graphs++ a compact generative model for semantic motion analysis and synthesis", ACM Transactions on Graphics(TOG), 31(6), pp.1~12 (2012)
- A. Safonova, "Construction and optimal search of interpolated motion graphs", ACM SIGGRAPH 2007 papers (2007)
- K. Grochow, "Style-based inverse kinematics", ACM SIGGRAPH 2004Papers, pp.522~531 (2004)