基于边缘智能的沉浸式元宇宙关键技术与展望

doi:10.11959/j.issn.2096-0271.2024001

大数据 ›› 2024, Vol. 10 ›› Issue (1): 35-45.doi: 10.11959/j.issn.2096-0271.2024001

• 研究 • 上一篇

基于边缘智能的沉浸式元宇宙关键技术与展望

王智¹, 夏树涛¹, 毛睿²

¹ 清华大学深圳国际研究生院，广东深圳 518055
² 深圳大学，广东深圳 518060

出版日期:2024-01-01 发布日期:2024-01-01
作者简介:王智（1985- ），男，清华大学深圳国际研究生院副教授，从事多媒体网络和系统方向研究，包括高性能数据处理系统优化、分布式机器学习系统、边缘计算与网络等。先后获得2017年教育部自然科学奖一等奖、2018年国家自然科学奖二等奖、2019年深圳市青年科技奖、2020年中国电子学会技术发明一等奖，入选中组部万人计划。研究成果获得多媒体领域高水平会议ACM Multimedia最佳论文奖、2014年计算机学会优秀博士论文奖。担任IEEE TMM副编辑和ACM TIST客座编辑。关键技术获得2014年移动互联网创业大赛第一名。研究成果获得工业届广泛应用和关注，相关成果被知名技术媒体MIT Technology Review、Synced Review等报道。
夏树涛（1972- ），男，清华大学深圳国际研究生院教授、博士生导师，计算机科学与技术研究所所长，深圳智能语义挖掘技术工程实验室主任。1997年1月博士毕业于南开大学数学系，2004年1月进入清华大学深圳研究生院，主要研究方向为编码/量化/压缩、机器学习/计算机视觉、AI安全等。在IEEE TIT、TPAMI、TSP、ToN、TDSC等国际权威期刊以及NIPS、ICML、ICLR、CVPR、ICCV、ECCV、ISIT等领域高端会议上发表学术论文100余篇。近年来主持完成国家973项目1项、国家重点研发计划项目1项、国家自然科学基金项目6项，以及深圳市重点科技项目多项。
毛睿（1975- ），男，长江特岗学者，深圳大学特聘教授、博士生导师，主要研究方向为通用大数据处理。现任深圳大学大数据系统计算技术国家工程实验室副主任，深圳计算科学研究院执行院长。提出了应对多样性挑战的大数据泛构模式，建立了基于度量空间的通用大数据管理分析理论框架，获6项国家、省部级或重要行业组织教学/科研奖励。
基金资助:
深圳市科技计划资助项目(JCYJ20220818101014030)

Edge-intelligence-based immersive metaverse:key technologies and prospects

Zhi WANG¹, Shutao XIA¹, Rui MAO²

¹ Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China
² Shenzhen University, Shenzhen 618060, China

Online:2024-01-01 Published:2024-01-01
Supported by:
Science and Technology Plan Project of Shenzhen(JCYJ20220818101014030)

摘要/Abstract

摘要：

近年来，360度视频、增强现实、虚拟现实等应用蓬勃发展，并逐渐形成元宇宙沉浸式体验新模式。这些新服务和应用具有高保真、沉浸式交互等共同特征。而作为一种新兴架构范式，边缘计算有效支持了这些需求。阐述释放边缘计算潜力支持沉浸式元宇宙体验的关键，包括AI驱动的内容生成；提出一种精度与延迟感知的模型推理框架，实现自适应深度学习模型部署和数据流推理，支撑用户体验感知的元宇宙服务与应用。

关键词: 边缘计算, 人工智能, 元宇宙, 沉浸式体验

Abstract:

In recent years, applications such as 360 video, augmented reality, virtual reality, etc.have been rapidly developed and gradually formed a new mode of immersive metaverse experience.These new services and applications have common features such as high fidelity and immersive interaction.As a new paradigm, edge computing is increasingly ready to support these features.This paper firstly elucidates that the key to releasing the power of edge computing to support immersive metaverse experience is the processing of AI models and data for content generation.Then, this paper presents a generic framework to realize adaptive deep learning model deployment and data flow to support metaverse services and applications.

Key words: edge computing, artificial intelligence, metaverse, immersive experience

中图分类号:

TP37

王智, 夏树涛, 毛睿. 基于边缘智能的沉浸式元宇宙关键技术与展望[J]. 大数据, 2024, 10(1): 35-45.

Zhi WANG, Shutao XIA, Rui MAO. Edge-intelligence-based immersive metaverse:key technologies and prospects[J]. Big Data Research, 2024, 10(1): 35-45.

图/表 3

参考文献 34

[1]	JENSEN J F , KJEMS E , LEHMANN N ,et al. Virtual space:spatiality in virtual inhabited 3D worlds[M].[S.l.]: Springer Science ＆ Business Media, 2002.
[2]	ZAHARIADIS T , DARAS P , BALLESTEROS L B ,et al. Towards future 3D media internet[EB]. NEM Summit, 2008.
[3]	LAEEQ K. Metaverse:why,how and what[Z]. 2022.
[4]	NING H , WANG H , LIN Y ,et al. A survey on metaverse:the state-ofthe-art,technologies,applications,and challenges[EB]. arXiv preprint, 2021,arXiv:2111.09673.
[5]	BALLARDINI R M , HE K , ROOS T . AI-generated content:authorship and inventorship in the age of artificial intelligence[M]// Online distribution of content in the EU.[S.l.]: Edward Elgar Publishing, 2019: 117-135.
[6]	LEE L H , BRAUD T , ZHOU P ,et al. All one needs to know about metaverse:a complete survey on technological singularity,virtual ecosystem,and research agenda[EB]. arXiv preprint, 2021,arXiv:2110.05352.
[7]	FANG Z X , CAI L B , WANG G . MetaHuman creator the starting point of the metaverse[C]// Proceedings of 2021 International Symposium on Computer Technology and Information Science. Piscataway:IEEE Press, 2021: 154-157.
[8]	PAWAR C S , GANATRA A , NAYAK A ,et al. Use of machine learning services in cloud[M]// Computer networks,big data and IoT. Singapore: Springer, 2021: 43-52.
[9]	HU C , JIANG J , WANG Z ,et al. Decentralized federated learning:a segmented gossip approach[EB]. arXiv preprint, 2019,arXiv:1908.07782.
[10]	DHELIM S , KECHADI T , CHEN L ,et al. Edge-enabled metaverse:the convergence of metaverse and mobile edge computing[EB]. arXiv preprint, 2022,2022,arXiv:2205.02764.
[11]	WU C L , WANG Z , SUN L F . PAAS:a preference-aware deep reinforcement learning approach for 360° video streaming[C]// Proceedings of the 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video. New York:ACM, 2021: 34-41.
[12]	WANG Y T , SU Z , ZHANG N ,et al. A survey on metaverse:fundamentals,security,and privacy[EB]. arXiv preprint, 2022,arXiv:2203.02662.
[13]	XU M , NG W C , LIM W Y B ,et al. A full dive into realizing the edge-enabled metaverse:visions,enabling technologies,and challenges[EB]. arXiv preprint, 2022,arXiv:2203.05471.
[14]	MACH P , BECVAR Z . Mobile edge computing:a survey on architecture and computation offloading[J]. IEEE Communications Surveys ＆ Tutorials, 2017,19(3): 1628-1656.
[15]	ZHANG J L , CHEN B , ZHAO Y C ,et al. Data security and privacy-preserving in edge computing paradigm:survey and open issues[J]. IEEE Access, 2018,6: 18209-18237.
[16]	朱锐, 王宏志, 崔双双 ,等. 面向元宇宙的云边端协同大数据管理[J]. 大数据, 2023,9(1): 63-77.
	ZHU R , WANG H Z , CUI S S ,et al. Cloud-edge-end collaborative big data management for metaverse[J]. Big Data Research, 2023,9(1): 63-77.
[17]	周知, 于帅, 陈旭 . 边缘智能:边缘计算与人工智能融合的新范式[J]. 大数据, 2019,5(2): 53-63.
	ZHOU Z , YU S , CHEN X . Edge intelligence:a new nexus of edge computing and artificial intelligence[J]. Big Data Research, 2019,5(2): 53-63.
[18]	NOMA T , ZHAO L , BADLER N I . Design of a virtual human presenter[J]. IEEE Computer Graphics and Applications, 2000,20(4): 79-85.
[19]	MA G , WANG Z , ZHANG M ,et al. Understanding performance of edge content caching for mobile video streaming[J]. IEEE Journal on Selected Areas in Communications, 2017,35(5): 1076-1089.
[20]	JIANG J Y , LUO Z Y , HU C H ,et al. Joint model and data adaptation for cloud inference serving[C]// Proceedings of 2021 IEEE Real-Time Systems Symposium. Piscataway:IEEE Press, 2021: 279-289.
[21]	SHAKER N , TOGELIUS J , NELSON M J . Procedural content generation in games[M]. Cham: Springer, 2016.
[22]	CRESWELL A , WHITE T , DUMOULIN V ,et al. Generative adversarial networks:an overview[J]. IEEE Signal Processing Magazine, 2018,35(1): 53-65.
[23]	WANG Z , WU S , XIE W ,et al. NeRF:neural radiance fields without known camera parameters[EB]. arXiv preprint, 2021,arXiv:2102.07064.
[24]	CHOUDHARY T , MISHRA V , GOSWAMI A ,et al. A comprehensive survey on model compression and acceleration[J]. Artificial Intelligence Review, 2020,53(7): 5113-5155.
[25]	CHEN C , YIN Y C , SHANG L F ,et al. bert2BERT:towards reusable pretrained language models[EB]. arXiv preprint, 2021,arXiv:2110.07143.
[26]	POLINO A , PASCANU R , ALISTARH D ,et al. Model compression via distillation and quantization[EB]. arXiv preprint, 2018,arXiv:1802.05668.
[27]	TANG C , OUYANG K , WANG Z ,et al. Mixed-precision neural network quantization via learned layer-wise importance[C]// Proceedings of European Conference on Computer Vision.[S.l.:s.n.], 2022.
[28]	HE Z L , LI H S , WANG Z ,et al. Adaptive compression for online computer vision:an edge reinforcement learning approach[J]. ACM Transactions on Multimedia Computing,Communications,and Applications, 2021,17(4): 1-23.
[29]	LI H S , HU C H , JIANG J Y ,et al. JALAD:joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution[C]// Proceedings of 2018 IEEE 24th International Conference on Parallel and Distributed Systems. Piscataway:IEEE Press, 2019: 671-678.
[30]	GOIAN H S , AL-JARRAH O Y , MUHAIDAT S ,et al. Popularity-based video caching techniques for cache-enabled networks:a survey[J]. IEEE Access, 2019,7: 27699-27719.
[31]	NARAYANAN A , VERMA S , RAMADAN E ,et al. DeepCache:a deep learning based framework for content caching[C]// Proceedings of the 2018 Workshop on Network Meets AI ＆ ML. New York:ACM, 2018: 48-53.
[32]	YE J H , LI Z C , WANG Z ,et al. Joint cache size scaling and replacement adaptation for small content providers[C]// Proceedings of IEEE INFOCOM 2021- IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2021: 1-10.
[33]	ZHOU S J , WANG Z , HU C H ,et al. Caching in dynamic environments:a near-optimal online learning approach[J]. IEEE Transactions on Multimedia, 2023,25: 792-804.
[34]	朱文武, 王智 . 数据驱动的网络多媒体边缘内容分发[J]. 中国科学(信息科学), 2021,51(3): 468-504.
	ZHU W W , WANG Z . Data-driven multimedia edge network and content delivery[J]. Scientia Sinica (Informationis), 2021,51(3): 468-504.

基于边缘智能的沉浸式元宇宙关键技术与展望

Edge-intelligence-based immersive metaverse:key technologies and prospects

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 34

相关文章 15

Metrics

推荐阅读 0

[1]	李国杰. 大数据与计算模型[J]. 大数据, 2024, 10(1): 9-16.
[2]	王皓, 潘昱杉, 潘毅. 生成式人工智能大模型赋能的元宇宙生命体：前瞻和挑战[J]. 大数据, 2023, 9(3): 85-96.
[3]	吴亚东, 陈家鸣, 罗焱, 王学锋, 黄德春, 倪超, 蓝集明, 李随群, 张巍瀚, 代唯. 彩灯元宇宙研究综述[J]. 大数据, 2023, 9(3): 97-113.
[4]	邓钇敏, 张旭龙, 司世景, 王健宗, 肖京. 虚拟人形象合成技术综述[J]. 大数据, 2023, 9(3): 114-139.
[5]	李婧文, 李雅文. 算法应用风险与治理研究[J]. 大数据, 2023, 9(3): 140-149.
[6]	刘烨, 成伟, 李焱, 尹依梦, 孙慧杰. 元宇宙视域下教育社区构建研究[J]. 大数据, 2023, 9(1): 78-86.
[7]	贺亚运, 彭俊清, 王健宗, 肖京. 节奏舞者：基于关键动作转换图和有条件姿态插值网络的3D舞蹈生成方法研究[J]. 大数据, 2023, 9(1): 23-37.
[8]	彭一非, 袁贞, 张旭龙, 姜桂林, 刘逾江. 基于数字孪生技术的元宇宙空气污染物浓度推断模型[J]. 大数据, 2023, 9(1): 38-50.
[9]	王子航, 禹向群, 斯洪标, 傅思敏, 张旭龙, 彭绍亮. 基于算力网络的元宇宙分层处理模型设计[J]. 大数据, 2023, 9(1): 51-62.
[10]	朱锐, 王宏志, 崔双双, 张恺欣, 燕钰. 面向元宇宙的云边端协同大数据管理[J]. 大数据, 2023, 9(1): 63-77.
[11]	何波. 元宇宙的法律难题与规制思路研究[J]. 大数据, 2023, 9(1): 87-102.
[12]	沈阳, 余梦珑. 元宇宙与大数据：时空智能中的数据洞察与价值连接[J]. 大数据, 2023, 9(1): 103-110.
[13]	李明, 吕阿斌. 隐私计算在车路协同场景应用的探索与实践[J]. 大数据, 2022, 8(5): 74-87.
[14]	王陈慧子, 蔡玮. 元宇宙数字经济：现状、特征与发展建议[J]. 大数据, 2022, 8(3): 140-150.
[15]	赵智韬, 赵理君, 张正, 唐娉. 基于容器云技术的典型遥感智能解译算法集成[J]. 大数据, 2022, 8(2): 58-74.