Seminars on Numerical Algorithms, Analyses, and Applications: Explicit geometric modeling based on implicit guidance

  • A+

:韩晓光(香港中文大学(深圳))
:2022-12-29 10:30
:腾讯会议ID:581-4735-3770(无密码)

报告人:韩晓光(香港中文大学(深圳))

时  间:1229日上午10:30-12:00

地  点:腾讯会议ID581-4735-3770(无密码)

内容摘要:

Explicit geometric representations, such as meshes, have long been the dominant representation in 3D modeling. In recent years, with the rise of 3D deep learning, implicit representations have been found to be well suited for learning-based geometric modeling frameworks and have achieved very good performance in numerous application domains. Should we continue to follow explicit expressions or develop implicit expressions? It has become a lively topic of discussion among researchers. This presentation will introduce two case studies and show how to effectively combine implicit and explicit representations to exploit the advantages of each: 1) geometric contour line deformation guided by implicit representations for efficient image instance segmentation (CVPR 2022 - SharpContour); 2) 3D mesh deformation guided by implicit representations for real-time interactive 3D character modeling (UIST 2021 - SimpModeling).

人简介:

韩晓光博士,现任香港中文大学(深圳)理工学院与未来智联网络研究院助理教授,校长青年学者,广东省杰青。他于2017年获得香港大学计算机科学专业博士学位。其研究方向包括计算机视觉和计算机图形学等,在该方向著名国际期刊和会议发表论文50余篇,包括顶级会议和期刊SIGGRAPH(Asia), CVPR, ICCV, ECCV, NeurIPS, ACM TOG, IEEE TPAMI等。他曾获得吴文俊人工智能优秀青年奖,目前也担任CVPR2023领域主席。他的工作曾获得CCF图形开源数据集奖(DeepFashion3D),Siggraph Asia 2013新兴技术最佳演示奖,2019年和2020年连续两年入选计算机视觉顶级会议CVPR最佳论文列表(入选率分别为0.8%0.4%),他是广东省珠江团队核心成员,以项目负责人身份主持NSFC青年和面上项目,阿里巴巴AIR计划,CCF犀牛鸟基金与腾讯AI Lab专项等,并以单位负责人参与NSFC-重点项目,国家重点研发计划,他的研究也受到华为、腾讯、阿里巴巴、思谋科技、红棉小冰、深圳市气象局等支持。

 

联系人:曹娟