欢迎访问江苏省计算机学会网站!    设为首页  |  收藏本站
江苏省计算机学会
  •  当前位置首页 > 新闻中心 > 通知公告
    新闻中心  
    党建工作
    学会动态
    政策法规
    行业新闻
    图片新闻
    通知公告
    学会通讯
     
    通知公告
    学术报告《Neural Modeling and Rendering: A Paradigm Shift in Computer Vision and Graphics》
    发布时间:2020-10-15 14:05:30

    南京大学计算机软件新技术国家重点实验室


    摘 要:

    Traditional computer graphics conducts accurate simulations by explicitly modeling surface geometry, surface reflectance and lighting via the rendering equation. They manage to produce high quality rendering but at an ultra-high computational cost. Conversely, traditional computer vision, in particular 3D reconstruction, seeks to recover camera pose, scene geometry, surface reflectance, etc, from the imagery data via techniques such as correspondence matching and bundle adjustment. In this talk, I present our recent efforts on employing neural modeling and rendering techniques to overcome the limitations in traditional rendering and 3D reconstruction. For graphics I demonstrate deep learning techniques that tackle unknown surface reflectance, corrupted/incomplete 3D shape, and volumetric opacity to produce unprecedented visual quality. For vision, I present a novel volumetric neural reconstruction framework that significantly outperforms state-of-the-art structure-from-motion and photometric stereo methods in reconstruction accuracy. Finally, I discuss how such neural representations may fundamentally change computer vision and graphics and potentially lead to a paradigm shift.  

    报告人简介:

    Jingyi Yu is currently Vice Provost of ShanghaiTech University, Professor and Executive Dean of the School of Information Science and Technology. He received B.S. from Caltech in 2000 and Ph.D. from MIT in 2005. He has published over 140 papers at highly refereed conferences and journals, and holds over 20 international patents on computer vision and computational imaging. He is a recipient of the NSF CAREER Award and has organized many international conferences in computer vision. He is a member of Shanghai AI Advisory Committee, and co-founder of DGene. He has been an Associate Editor of IEEE TPAMI, IEEE TIP, and Elsevier CVIU. He was a program chair of ICCP 2016, ICPR 2020 and WACV 2021, and will be a program chair of two top AI conferences, IEEE CVPR 2021 and ICCV 2025.

    时间:10月16日 11:00-12:00

    地点:计算机科学技术楼230室



    上一篇:学术报告《区块链技术基本原理及应用》
    下一篇:技术创新论坛《Vision + Language: From Captioning to Grounding》
    友情链接:
    江苏省科学技术协会 中国计算机学会 南京大学 南京大学计算机科技与技术系 南京大学软件学院 东南大学计算机科学与工程学院 江苏经贸职业技术学院 南京信息职业技术学院 南京工业职业技术学院 江苏海事职业技术学院 常州信息职业技术学院 国网电力科学研究院 电子科技集团第28研究所 江南计算技术研究所 
       
     

    Copyright (c) 版权所有 江苏省计算机学会          南京网站建设公司
    秘书处办公室       地址: 江苏省南京市仙林大道163号  邮编:210023   电话/传真:025-89680909   
    秘书处市内联络点   地址: 江苏省南京市汉口路22号     邮编:210093   电话/传真:025-86635622
    电子邮箱:jscs@nju.edu.cn   网址:www.jscs.org.cn    技术支持:南京成旭通信息技术有限公司  

    网站备案号:苏ICP备14049275号-1

    您是本站第27318769位来客!

    在线客服

    点击这里给我发消息