Filters








15,838 Hits in 6.6 sec

A Survey on Human Performance Capture and Animation

Shihong Xia, Lin Gao, Yu-Kun Lai, Ming-Ze Yuan, Jinxiang Chai
2017 Journal of Computer Science and Technology  
Key research problems include how to capture and analyze static geometric appearance and dynamic movement of human bodies, and how to simulate human body motions with physical effects.  ...  Human performance mainly involves human body shapes and motions.  ...  Current human motion synthesis methods are mainly composed of the following three types: (1) data-driven human body motion synthesis, (2) physics-based human body motion synthesis, and (3) human body motion  ... 
doi:10.1007/s11390-017-1742-y fatcat:kxfoylv535axtnpj6iaqda3mz4

3D Human Motion Editing and Synthesis: A Survey

Xin Wang, Qiudi Chen, Wanliang Wang
2014 Computational and Mathematical Methods in Medicine  
This paper presents a comprehensive survey of 3D human motion editing and synthesis techniques. Firstly, four types of methods for 3D human motion synthesis are introduced and compared.  ...  Secondly, motion capture data representation, motion editing, and motion synthesis are reviewed successively. Finally, future research directions are suggested.  ...  Y1110882, Y1110688, and R1110679), and Higher School Specialized Research Fund for the Doctoral Program (no. 20113317110001).  ... 
doi:10.1155/2014/104535 pmid:25045395 pmcid:PMC4089843 fatcat:ocfjgofomrdwnkjrz24nn4gk3i

Audio-driven human body motion analysis and synthesis

F. Ofli, C. Canton-Ferrer, J. Tilmanne, Y. Demir, E. Bozkurt, Y. Yemez, E. Erzin, A. M. Tekalp
2008 Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing  
This paper presents a framework for audio-driven human body motion analysis and synthesis.  ...  The human body posture is extracted from multiview video information without any human intervention using a novel marker-based algorithm based on annealing particle !ltering.  ...  This motion pattern is represented by the kinematic constrains and physical limits of the joints of the human body.  ... 
doi:10.1109/icassp.2008.4518089 dblp:conf/icassp/OfliCTDBYET08 fatcat:73prooupprfn7icvfmifvhfusi

A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos [article]

Thiago L. Gomes and Renato Martins and João Ferreira and Rafael Azevedo and Guilherme Torres and Erickson R. Nascimento
2021 arXiv   pre-print
Transferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision.  ...  We also present a new video retargeting benchmark dataset composed of different videos with annotated human motions to evaluate the task of synthesizing people's videos, which can be used as a common base  ...  The authors thank CAPES, CNPq, and FAPEMIG for funding this work. We also thank NVIDIA for the donation of a Titan XP GPU used in this research.  ... 
arXiv:2103.15596v2 fatcat:them7wrlvfchpgy36mtxmfzm2q

Application of Heterogenous Motion Models towards Structure Recovery from Motion [chapter]

Rohith M.V., Chandra Kambhamettu
2013 Lecture Notes in Computer Science  
We tested our method on data from human motion capture for objective analysis and provide results on natural videos.  ...  In this paper, we present a scheme for structure recovery based on motion classification and automatic selection of reconstruction algorithms for each scene object.  ...  Introduction Non-rigid structure from motion algorithms are being explored for a variety of applications such as 2D to 3D conversion of existing video sequences, human motion analysis and human computer  ... 
doi:10.1007/978-3-642-37331-2_47 fatcat:hjh2ckwi4vfvbhikb43kloao3m

Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints [article]

Thiago L. Gomes and Renato Martins and João Ferreira and Erickson R. Nascimento
2020 arXiv   pre-print
Marker-less human motion estimation and shape modeling from images in the wild bring this challenge to the fore.  ...  In this paper, we propose a unifying formulation for transferring appearance and retargeting human motion from monocular videos that regards all these aspects.  ...  The authors would like to thank CAPES, CNPq, FAPEMIG, and ATMOSPHERE PROJECT for funding different parts of this work.  ... 
arXiv:2001.02606v2 fatcat:m2cposgyqneqvnxsxznrtr4akm

Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints

Thiago L. Gomes, Renato Martins, Joao Ferreira, Erickson R. Nascimento
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Marker-less human motion estimation and shape modeling from images in the wild bring this challenge to the fore.  ...  In this paper, we propose a unifying formulation for transferring appearance and retargeting human motion from monocular videos that regards all these aspects.  ...  The authors would like to thank CAPES, CNPq, and FAPEMIG for funding different parts of this work. We also thank NVIDIA Corporation for the donation of a Titan XP GPU used in this research.  ... 
doi:10.1109/wacv45572.2020.9093395 dblp:conf/wacv/GomesMFN20 fatcat:mwmpbph2ozbmfieitekagcwcpq

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics [article]

Evonne Ng, Shiry Ginosar, Trevor Darrell, Hanbyul Joo
2021 arXiv   pre-print
We demonstrate the efficacy of our method on hand gesture synthesis from body motion input, and as a strong body prior for single-view image-based 3D hand pose estimation.  ...  We propose a novel learned deep prior of body motion for 3D hand shape synthesis and estimation in the domain of conversational gestures.  ...  This enables learning gestural patterns in both person-specific and population-level domains. 3D hand synthesis Prior physics-based 3D hand synthesis approaches [28, 36, 46] generate motion patterns  ... 
arXiv:2007.12287v3 fatcat:vgwbijprbvenjjnura3yvohtgu

Sports Video Panorama Synthesis Technology Based on Edge Computing and Video Shot Boundary Detection

Xu Chen, Xin Ning
2022 Wireless Communications and Mobile Computing  
The synthesis technology for sports video panorama is investigated in this paper using edge computing and video shot boundary detection.  ...  and development of video panorama technology in the actual training process, are not only an important response to the current characteristics of students' physical education learning and physical and  ...  It can be seen that the speed and accuracy of the global motion estimation algorithm for motion video can be improved.  ... 
doi:10.1155/2022/4060852 fatcat:5lknhg7lqvcutg6xkzpfaawt3e

Human motion synthesis from 3D video

Peng Huang, Adrian Hilton, Jonathan Starck
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we present a framework for concatenative synthesis from multiple 3D video sequences according to user constraints on movement, position and timing.  ...  Multiple 3D video sequences of an actor performing different movements are automatically constructed into a surface motion graph which represents the possible transitions with similar shape and motion  ...  In this paper, we extend example-based methods for motion synthesis from conventional motion capture to 3D video.  ... 
doi:10.1109/cvpr.2009.5206626 dblp:conf/cvpr/HuangHS09 fatcat:olr4qbso5jfivnbnqfjdi6kbcu

Human motion synthesis from 3D video

Peng Huang, A. Hilton, J. Starck
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we present a framework for concatenative synthesis from multiple 3D video sequences according to user constraints on movement, position and timing.  ...  Multiple 3D video sequences of an actor performing different movements are automatically constructed into a surface motion graph which represents the possible transitions with similar shape and motion  ...  In this paper, we extend example-based methods for motion synthesis from conventional motion capture to 3D video.  ... 
doi:10.1109/cvprw.2009.5206626 fatcat:tmv2mhtdlba65pybq3eu5smxbi

Neural Kinematic Networks for Unsupervised Motion Retargetting

Ruben Villegas, Jimei Yang, Duygu Ceylan, Honglak Lee
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We also demonstrate motion retargetting from monocular human videos to 3D characters using an off-the-shelf 3D pose estimator.  ...  Abstract We propose a recurrent neural network architecture with a Forward Kinematics layer and cycle consistency based adversarial training objective for unsupervised motion retargetting.  ...  This work was supported in part by Gift from Adobe Research, NSF CAREER IIS-1453651, and Rackham Merit Fellowship. We would like to thank Aaron Hertzmann for helpful discussions.  ... 
doi:10.1109/cvpr.2018.00901 dblp:conf/cvpr/VillegasYCL18 fatcat:clvz2m7ssvfxrellhbfd2mfp5y

Learning to Generate Diverse Dance Motions with Transformer [article]

Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler, Hao Li
2020 arXiv   pre-print
As motion capture data is limited for the range of dance motions and styles, we introduce a massive dance motion data set that is created from YouTube videos.  ...  We introduce a complete system for dance motion synthesis, which can generate complex and highly diverse dance sequences given an input music sequence.  ...  We thank Yajie Zhao, Mingming He for prof reading, Zhengfei Kuang for editing the demo, Marcel Ramos and Kalle Bladin for the character rigging and rendering, and Pengda Xiang for the data annotation.  ... 
arXiv:2008.08171v1 fatcat:kp57scjce5cnlejdqpukvhurem

Guest Editorial: Human Activity Understanding from 2D and 3D Data

Junsong Yuan, Wanqing Li, Zhengyou Zhang, David Fleet, Jamie Shotton
2016 International Journal of Computer Vision  
; realistic synthesis and animation of human motion; and monitoring of elderly and disabled people at home.  ...  Recent advances in 3D depth cameras using structured light or time-of-flight sensors, 3D information recovery from 2D images/videos, and the availability of portable human motion capture devices have made  ...  ; realistic synthesis and animation of human motion; and monitoring of elderly and disabled people at home.  ... 
doi:10.1007/s11263-016-0915-4 fatcat:vb7rahjb2vd37lcpom3k74znma

Analysis of Co-Laughter Gesture Relationship on RGB videos in Dyadic Conversation Contex [article]

Hugo Bohy, Ahmad Hammoudeh, Antoine Maiorca, Stéphane Dupont, Thierry Dutoit
2022 arXiv   pre-print
This work studies the relationship between laughter and body movements in dyadic conversations. The body movements were extracted from videos using deep learning based pose estimator model.  ...  However, we did not find a direct correlation between audio features and body movements. We discuss about the challenges to use such dataset for the audio-driven co-laughter motion synthesis task.  ...  The motion data is not extracted from motion capture sensors but is estimated from the recorded RGB videos directly.  ... 
arXiv:2205.10266v1 fatcat:2xzdjrrbpbbp3pjygwynscx23e
« Previous Showing results 1 — 15 out of 15,838 results