腾讯
腾讯是一家世界领先的互联网科技公司，用创新的产品和服务提升全球各地人们的生活品质。腾讯成立于1998年，总部位于中国深圳。公司一直秉承科技向善的宗旨。我们的通信和社交服务连接全球逾10亿人，帮助他们与亲友联系，畅享便捷的出行、支付和娱乐生活。腾讯发行多款风靡全球的电子游戏及其他优质数字内容，为全球用户带来丰富的互动娱乐体验。腾讯还提供云计算、广告、金融科技等一系列企业服务，支持合作伙伴实现数字化转型，促进业务发展。
云与智慧产业事业群
腾讯旗下的云与智慧产业事业群（CSIG）成立于2018年9月30日，致力于推进云与产业互联网战略，依托云、安全、人工智能等技术创新，打造智慧产业升级方案。探索用户与产业的创新互动，打通产业上下游不同企业，联动线上线下的场景与资源，助力零售、医疗、教育、交通等产业数字化升级，同时协助企业更智能地服务用户，构建连接用户与商业的智慧产业新生态。
腾讯多媒体实验室
腾讯多媒体实验室作为腾讯云与智慧产业事业群的核心实验室之一，专注于多媒体技术领域的前沿技术探索、研发、应用和落地，包含音视频编解码、网络传输和实时通信，基于信号处理和深度学习的多媒体内容处理、分析、理解和质量评估，沉浸式媒体（VR、AR、点云等）系统设计和端到端解决方案；同时负责国际国内行业标准制定，包含多媒体数据压缩，网络传输协议，多媒体系统和开源平台等。腾讯多媒体实验室标准团队的研究领域包括图片、音频和视频的压缩、传输和AI。实验室成员积极参与相关的工业论坛，以技术推动产业的发展。腾讯多媒体实验室积极参与JVET、MPEG、VCEG、AVS、AOM、Video Quality Standards、3GPP、IETF等国际核心标准组织，拥有高效的视频编解码器，支持H.264, H.265, H.266, VP9，AV1，AVS2，AVS3等国际国内标准格式。实验室专家在各标准组织中担任重要职务，在深入标准研究制定的同时积极推动标准技术落地，广泛应用服务于腾讯各业务线。
腾讯多媒体实验室专家成员
刘杉
腾讯集团杰出科学家
腾讯多媒体实验室负责人
刘杉，现任腾讯杰出科学家和腾讯多媒体实验室负责人，本科毕业于清华大学电子工程系，硕士和博士毕业于美国南加州大学电气工程系。刘杉博士曾任职多家全球500强和国际知名企业并担任高级技术和管理职务。自2017年加入腾讯，组建标准团队并代表腾讯在多媒体系统，数据压缩和网络传输协议等国际标准领域取得突破性成果。同时，带领团队研发和交付多项多媒体核心技术，应用于腾讯旗下多款产品，包含腾讯会议，腾讯云投屏，腾讯云游戏，QQ视频通话，腾讯影业，腾讯文旅，微视，全民K歌等，服务DAU千万用户，进而积极投入开源云平台和生态建设。刘杉博士深耕多媒体技术领域20年，是超过100篇学术论文的作者和超过300个已授权专利的发明人，是已发布国际标准ISO/IEC/ITU-T H.265/HEVC SCC和H.266/VVC的联合主编。她曾多次担任国际标准专题组主席和联席主席，并于2019年至今担任IEEE数据压缩标准委员会副主席。刘杉博士于2018年荣获亚太信号与信息处理协会工业领袖称号，并于2020年荣登福布斯中国科技女性榜。
李松南
腾讯多媒体实验室总监
李松南，腾讯多媒体实验室总监，带领团队研发了基于信号处理和深度学习的多媒体内容处理、分析、理解等多项技术与产品。研究包括图像降噪、人脸重建、三维跟踪、图像质量评估、视频编解码等方向，相关成果在 TPAMI、TMM、TCSVT、TIP、CVPR 等计算机视觉、图像处理领域顶级期刊和会议上发表。
李翔
腾讯多媒体实验室标准负责人
李翔，腾讯多媒体实验室行业标准中心总监，资深专家研究员。李翔博士深耕视频编解码领域多年，是国际视频编解码标准的积极贡献者，并担任包括JEM参考软件联席主席、VVC参考软件联席主席、MPEG-5 EVC标准联合编辑等多个专家小组主席/联席主席职位。李翔博士是IEEE高级会员，在相关领域顶级期刊和学术会议发表论文50多篇，提交标准提案数百个，持有美国授权专利及公开专利申请近500件。
Stephan Wenger
腾讯知识产权与标准高级总监
Stephan Wenger，腾讯知识产权与标准高级总监。加入腾讯之前，他曾任统一协作解决方案提供商Vidyo公司知识产权与标准副总裁，积极参与多个多媒体技术标准化组织，如IETF、ITU-T和MPEG。Wenger博士持有40多个已授权专利以及更多的专利申请。
赵欣
腾讯多媒体实验室专家研究员
赵欣，腾讯多媒体实验室专家研究员，专注于新一代视频压缩算法的研发工作及开放媒体联盟（AOM）旗下的标准制定工作。赵欣博士在视频编码和处理技术领域深耕超过12年，在该领域有着丰富的从业经验，积极参与国际视频标准及其扩展标准的制定工作，主持核心技术实验及担任多项BoG和AhG的主席，拥有超过260项专利申请，其中包括20多项已授权专利，已发表40多篇著名国际期刊及会议论文。
Iraj Sodagar
腾讯多媒体实验室专家研究员
Iraj Sodagar，腾讯多媒体实验室专家研究员。加入腾讯之前，他在微软担任多媒体系统主任架构师。他在多个标准组织中担任领导职位，如in ITU-T, JPEG, MPEG, AMQP, W3C, DVB, 3GPP, W3C, CTA WAVE, DLNA 以及AOMedia。他在21世纪初开创了第一个关于移动视频交付的工业论坛——无线媒体论坛。自MPEG DASH开始以来，他一直担任主席职务。他建立了DASH工业论坛，并任主席和董事长。此外，他担任MPEG CMAF联席主席至CMAF第一版本发布。
许晓中
腾讯多媒体实验室专家研究员
许晓中，腾讯多媒体实验室专家研究员，积极参与H.264/AVC, H.265/HEVC, H.266/VVC, MPEG-5, ITU-T IPTV, AVS等一系列国际国内视频标准制定，提交超过300个技术提案，并有多于100项技术提案被各个标准化组织所采纳。许晓中博士积极推动行业标准的发展，目前担任HEVC SCC, VVC 及AVS等标准组织的屏幕内容编码专题小组的联合主席，AVS质量评价组组长，MPEG-5标准文本联合编辑等职务。
朱斌
腾讯多媒体实验室专家研究员
朱斌，腾讯多媒体实验室专家研究员。加入腾讯之前，他在Intel，Apple带领技术团队负责视频核心技术开发。2018年12月加入公司以来，朱斌博士带领团队积极推动下一代视频编解码国际标准VVC/H.266编解码器的实现，优化和开源协同。
论文成就
基于深厚的技术积累，腾讯多媒体实验室目前已经累计向国际和国家多个视频标准组织提交了数百篇屏幕内容编码技术提案 (其中超过50项被标准组织采纳)，相关技术已申请专利百余项。
学术论文方面，腾讯多媒体实验室团队相关工作发表在ICIP2020，ICASSP2021，ICME2021，ICIP2021，PCS 2021，百余篇高质量学术论文被接收或已发表。实验室的专家也受邀在VCIP，ICME，ICIP等多个行业主流国际会议上进行屏幕内容编码技术专题讲座，担任多个专题研讨会主席，积极推动该技术领域的进展。
腾讯多媒体实验室论文-部分
（已发布/已录用）
上下拉动翻看这个书签
1. M. Krishna, X. Zhao, S. Liu, "Multicomponent Secondary Transform", accepted by 2021 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2021
2. X. Xu, S. Liu and Z. Li, "A Video Dataset for Learning-based Visual Data Compression and Analysis", accepted by 2021 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2021
3. Y. Du, X. Zhao, S. Liu, "Cross-Component Sample Offset For Image And Video Coding", accepted by 2021 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2021
4. P. Garus, F. Henry, J. Jung, T. Maugey and C. Guillemot, "Immersive Video Coding: Should Geometry Information be Transmitted as Depth Maps?," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3100006.
5. W. -J. Chien, L. Zhang, M. Winken, X. Li, R.-L. Liao, H. Gao, C.-W. Hsu, H. Liu, C.-C. Chen, "Motion Vector Coding and Block Merging in Versatile Video Coding Standard," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3101212.
6. Y. -W. Huang, J. An, H. Huang, X. Li, S.-T. Hsiang, K. Zhang, H. Gao, J. Ma, O. Chubach, "Block Partitioning Structure in the VVC Standard," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3088134.
7. X. Zhao, S.-H. Kim, Y. Zhao, H. E. Egilmez, M. Koo, S. Liu, J. Lainema, M. Karczewicz, "Transform Coding in the VVC Standard," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3087706.
8. S. Kahu, M. Krishnan, X. Zhao and S. Liu, “Context-Adaptive Secondary Transform for Video Coding,” Accepted by 2021 IEEE International Conference on Image Processing (ICIP), Sep. 2021, Alaska, USA.
9. L. Zhao, X. Zhao and S. Liu, “Semi-Decoupled Partitioning for Video Coding beyond AV1,” Accepted by 2021 IEEE International Conference on Image Processing (ICIP), Sep. 2021, Alaska, USA.
10. Y. -K. Wang, R. Skupin, M. M. Hannuksela, S. Deshpande, Hendry, V. Drugeon, R. Sjöberg, B.D. Choi, V. Seregin, Y. Sanchez, J. M. Boyce, W. Wan, G. J. Sullivan, "The High-Level Syntax of the Versatile Video Coding (VVC) Standard," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3070860.
11. Y. Li, S. Liu, Y. Chen, Y. Zheng, S. Chen, B. Zhu, J. Lou, "An Optimized H.266/VVC Software Decoder On Mobile Platform," 2021 Picture Coding Symposium (PCS), 2021, pp. 1-5, doi: 10.1109/PCS50896.2021.9477484.
12. Y. Wang, X. Xu and S. Liu, "Low Complexity Implementation Of Intra String Copy In Avs3," 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2021, pp. 1-4, doi: 10.1109/ICMEW53276.2021.9456015.
13. L. Wang, X. Xu and S. Liu, "Enhanced Implicit Selection of Transform Skip in AVS3," 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6, doi: 10.1109/ICME51207.2021.9428251.
14. B. Zhu, S. Liu, Y. Liu, Y. Luo, J. Ye, H. Xu, Y. Huang, H. Jiao, X. Xu, X. Zhang, C. Gu, "A Real-Time H.266/VVC Software Decoder," 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6, doi: 10.1109/ICME51207.2021.9428470.
15. W. Jiang, W. Wang, S. Liu, S. Li, "PnG: Micro-structured Prune-and-Grow Networks for Flexible Image Restoration", NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges at CVPR 2021.
16. X. Zhao, S. Liu, X. Li, G. Li and X. Xu, "Video Coding Tool Analysis and Dataset for Gaming Content," 2021 Picture Coding Symposium (PCS), 2021, pp. 1-5, doi: 10.1109/PCS50896.2021.9477454.
17. X. Zhao, L. Zhao, M. Krishnan, Y. Du, S. Liu, D. Mukherjee, Y. Xu, A. Grange, "Study On Coding Tools Beyond AV1," 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6, doi: 10.1109/ICME51207.2021.9428244.
18. Y. Jin, L. Zhao, X. Zhao, S. Liu and A. C. Bovik, "Improved Intra Mode Coding Beyond Av1," ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 1580-1584, doi: 10.1109/ICASSP39728.2021.9413420.
19. J. M. Boyce, R. Doré, A. Dziembowski, J. Fleureau, J. Jung, B. Kroon, B. Salahieh, V. K. M. Vadakital, L. Yu, "MPEG Immersive Video Coding Standard," in Proceedings of the IEEE, vol. 109, no. 9, pp. 1521-1536, Sept. 2021, doi: 10.1109/JPROC.2021.3062590.
20. J. Pfaff, A. Filippov, S. Liu, X. Zhao, J. Chen, S. De-Luxan-Hernandez, T. Wiegand, V. Rufitskiy, A. K. Ramasubramonian; G. Van der Auwera "Intra Prediction and Mode Coding in VVC," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3072430.
21. T. Nguyen，X. Xu, F. Henry, R.-L. Liao, M. Sarwer; M. Karczewicz; Y.-H. Chao, J. Xu, S. Liu, D. Marpe, G. J. Sullivan, "Overview of the Screen Content Support in VVC: Applications, Coding Tools, and Performance," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3074312.
22. S. Liu, A. Segall, E. Alshina, R.-L. Liao， ”Common Test Conditions and evaluation procedures for neural network-based video coding technology“，ISO/IEC JTC1/SC29/WG11 JVET-U2016， Jan. 2021.
23. Q. Cai, Z. Chen, D. Wu, S. Liu and X. Li, "A Novel Video Coding Strategy in HEVC for Object Detection," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3056134.
24. Z. Zhang, X. Zhao, X. Li, L. Li, Y. Luo, S. Liu and Z. Li, "Fast DST-VII/DCT-VIII With Dual Implementation Support for Versatile Video Coding," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 1, pp. 355-371, Jan. 2021.
25. X. Zhang and W. Gao, "Adaptive Geometry Partition for Point Cloud Compression", in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3101807.
26. X. Xu, S. Liu, “Overview of Screen Content Coding in Recently Developed Video Coding Standards”, in IEEE Transactions on Circuits and Systems for Video Technology. DOI: 10.1109/TCSVT.2021.3064210.
27. H. Kirchhoffer, P. Haase, W. Samek, K. Müller, H. R.-Tavakoli, F. Cricri, E. Aksu, M. M. Hannuksela, W. Jiang, W. Wang, S. Liu, S. Jain, S. H.- Rad, F. Racapé, W. Bailer, "Overview of the Neural Network Compression and Representation (NNR) Standard", in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3095970.
28. X. Xu and S. Liu, "Screen Content Coding in Recently Developed Video Coding Standards," 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020, pp. 1-2, doi: 10.1109/VCIP49819.2020.9301789.
29. X. Xu, S. Wang, Y. Chen, Y. Li, Q. Zhang, Y. Zheng and S. Liu, "An Optimized Video Encoder Implementation with Screen Content Coding Tools", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP).
30. X. Zhao and S. Liu, “Unified Secondary Transform for Intra Coding Beyond AV1,” 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp. 3393-3397.
31. L. Zhao, X. Zhao and S. Liu, “Improved Intra Coding Beyond AV1 Using Adaptive Prediction Angles and Reference Lines,” 2020 IEEE International Conference on Image Processing, Abu Dhabi, United Arab Emirates, 2020, pp. 3408-3412.
32. X. Zhao, S. Liu, L. Zhao, X. Xu, B. Zhu, X. Li, "A comparative study of HEVC, VVC, VP9, AV1 and AVS3 video codecs," Proc. SPIE 11510, Applications of Digital Image Processing XLIII, 1151011, 21 Aug. 2020.
33. Y. Hu, Y. Li, Z. Chen, X. Xu and S. Liu, "Performance Analysis of Intra Block Copy for Screen Content Coding in AVS3", IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2020.
34. Y. Wang, X. Xu and S. Liu, "Intra Block Copy in AVS3 Video Coding Standard", IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2020.
35. H. Zhu, X. Xu and S. Liu, "Residual convolutional neural network based in-loop filter with intra and inter Frames Processed Respectively for AVS3", IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2020.
36. ”Vaccine-style-net: Point Cloud Completion in Implicit Continuous Function Space“, ACM MM 2020
37. “Context-aware Attention Network For Predicting Image Aesthetic quality Subjectivity”, ACM MM 2020
38. “A point cloud compression framework via spherical projection”, 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
39. “Fast Recolor Prediction Scheme in Point Cloud Attribute Compression”, 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
40. “Learning Disentangled Representation for Multi-View 3D Object Recognition”, IEEE Trans CSVT
41. “Nested Error Map Generation Network for No-Reference Image Quality Assessment”, 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
42. “Deep Neural Networks for End-to-End Spatiotemporal Video Quality Prediction and Aggregation”, 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021
43. Y. Zhang, Z. Chen, S. Liu, ”Video Super Resolution Using Temporal Encoding ConvLSTM and Multi-Stage Fusion”, Submitted to 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
44. “Deep Inter Coding with Interpolated Reference Frame for Hierarchical Coding Structure”, 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
45. "Towards Quantized DCT Coefficients Restoration for Compressed Images", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
46. "No-reference Quality Assessment of Panoramic Video based on Spherical-domain Features", 2021 IEEE International Conference on Picture Coding Symposium (PCS), 2021
47. "No-reference Quality Assessment of Panoramic Video based on Spherical-domain Features", IEEE Trans. IP
48. "A Spatial-Temporal Recurrent Neural Network for Video Saliency Prediction", IEEE Trans. IP
49. "Semantic Information Oriented No-Reference Video Quality Assessment", IEEE Signal Processing Letters
50. "Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
51. "Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
52. "Shape-Preserving Stereo Object Remapping via Object-Consistent Grid Warping", IEEE Trans. IP
53. "YOCO: Light-Weigth Rate Control Model Learning", 2020 IEEE International Conference on Image Processing (ICIP), 2020
54. "Residual Guided Deblocking with Deep Learning", 2020 IEEE International Conference on Image Processing (ICIP), 2020
55. "Network Update Compression for Federated Learning", 2020 IEEE International Conference on Image Processing (ICIP), 2020
56. "Network Update Compression for Federated Learning", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
57. "Video-based Point Cloud Compression Artifact Removal", IEEE Trans. MM
58. "Convolutional Neural Network-based Occupancy Map Accuracy Improvement for Video-based Point Cloud Compression", IEEE Trans. MM
59. "Occupancy-Map-Based Rate Distortion Optimization and Partition for Video-Based Point Cloud Compression", IEEE Trans. CSVT
60. "Fast DST-VII/DCT-VIII With Dual Implementation Support for Versatile Video Coding", IEEE Trans. CSVT
61. "Learning Model-Blind Temporal Denoisers without Ground Truths", 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
62. "Deep Learning-Based Technology in Responses to the Joint Call for Proposals on Video Compression With Capability Beyond HEVC", IEEE Trans. CSVT
63. "Cross-modal Relational Reasoning Network for Visual Question Answering", ICCV 2021 Mair2 Workshop
64. "Adaptive Geometry Partition for Point Cloud Compression", IEEE Trans. CSVT
65. "Point Cloud Geometry Prediction Across Spatial Scale using Deep Learning", 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 2020
66. "Implicit Geometry Partition for Point Cloud Compression", IEEE DCC 2020
67. "Linear Model based Geometry Coding for Lidar Acquired Point Clouds", IEEE DCC 2020
68. "PNG: Micro-structured prune-and-grow networks for flexible image restoration", CVPR 2021 NTIRE Workshop, 2021
69. "Structured weight unification and encoding for neural network compression and acceleration", CVPR 2021 Workshop, 2021
70. L. Zhao et al., "Wide Angular Intra Prediction for Versatile Video Coding," 2019 Data Compression Conference (DCC), 2019, pp. 53-62.
71. Y. -J. Chang et al., "Multiple Reference Line Coding for Most Probable Modes in Intra Prediction," 2019 Data Compression Conference (DCC), 2019.
72. Z. Zhang, X. Zhao, X. Li, Z. Li and S. Liu, "Fast Adaptive Multiple Transform for Versatile Video Coding," 2019 Data Compression Conference (DCC), 2019, pp. 63-72.
73. Y.-J. Chang, H.-J. Jhu, H.-Y. Jian, L. Zhao, X. Zhao, X. Li, S. Liu, B. Bross, P. Keydel, H. Schwarz, D. Marpe, T. Wiegand, "Intra prediction using multiple reference lines for the versatile video coding standard," Proc. SPIE 11137, Applications of Digital Image Processing XLII, 1113716, 6 Sep. 2019.
74. X. Xu, X. Li and S. Liu, "Intra block copy in Versatile Video Coding with Reference Sample Memory Reuse", Picture Coding Symposium (PCS) 2019.
75. X. Xu and S. Liu, "Recent advances in video coding beyond the HEVC standard", APSIPA Trans. on Signal and Information Processing, vol. 8, pp. e18, Jun. 2019.
76. X. Xu, X. Li and S. Liu, "Current Picture Referencing in Versatile Video Coding", IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2019.
77. X. Zhao, L. Li, Z. Li, X. Li and S. Liu, "Coupled Primary and Secondary Transform for Next Generation Video Coding," 2018 IEEE Visual Communications and Image Processing (VCIP), 2018, pp. 1-4.
78. X. Xu, X. Li and S. Liu, "Intra Block Copy for Next Generation Video Coding", IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2018.
未来憬愿
未来，腾讯多媒体实验室将继续努力，积极参与相关国际大会和工业论坛，发表更多高质量的文论，并以技术推动产业发展，在增加中国互联网技术国际影响力的同时，持续为多媒体领域的发展做贡献。腾讯多媒体实验室将秉承腾讯集团的使命与愿景，一切以用户价值为依归，将社会责任融入产品及服务之中，推动科技创新与文化传承，助力各行各业升级，促进社会的可持续发展，研发更好的技术更好地为人民用户服务，科技向善。
请随时与我们联系并分享您的需求：
腾讯多媒体实验室
medialab@tencent.com
作者：张意晗
编辑：张意晗
