GAMES Webinar 2022 – 246期(三维生成与重建) | Lingjie Liu(The University of Pennsylvania / Max Planck Institute for Informatics)，Zhiqin Chen(Simon Fraser University)
【GAMES Webinar 2022-246期】(视觉专题-三维生成与重建)
报告嘉宾：Lingjie Liu(The University of Pennsylvania / Max Planck Institute for Informatics)
报告时间：2022年9月8号星期四晚上20:00-20:45（北京时间）
报告题目：Photo-realistic 3D-aware Scene Generation
报告摘要：
The immense success of deep learning has demonstrated the importance of large-scale training data. However, the bottleneck of applying deep learning for 3D tasks is the lack of high-quality 3D data with corresponding photo-realistic imagery. In this talk, I will introduce our recent work on 3D-aware generative models that create photo-realistic novel scene contents only from easily accessible single-view 2D images. Finally, I will discuss the challenges and opportunities in this area for future work.
讲者简介：
Lingjie Liu is an incoming tenure-track Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania, where she will be leading the Computer Graphics Lab. Currently, Lingjie Liu is a Lise Meitner Postdoctoral Research Fellow at Max Planck Institute for Informatics. She received her Ph.D. degree at the University of Hong Kong in 2019. Before that, she got her B.Sc. degree in Computer Science at Huazhong University of Science and Technology in 2014. Her research interests include neural scene representations, neural rendering, human performance modeling and capture, and 3D reconstruction.
个人主页：https://lingjie0206.github.io/
报告嘉宾：Zhiqin Chen(Simon Fraser University)
报告时间：2022年9月8号星期四晚上20:45-21:30（北京时间）
报告题目：Neural Mesh Reconstruction
报告摘要：
Triangle meshes, despite being the dominant 3D shape representation for most real-world applications, are not as popular as other representations in neural 3D shape reconstruction. One major reason is that triangle tessellations are irregular and generating them seems incompatible with neural networks. In this presentation, I will introduce how we bypass the issue by storing meshes in regular grid structures. I will briefly describe our recent works on reconstructing triangle meshes from signed inputs such as signed distance fields or binary voxels (“Neural Marching Cubes”), from unsigned inputs such as unsigned distance fields or point clouds (“Neural Dual Contouring”), and from multi-view images (“MobileNeRF”).
讲者简介：
Zhiqin is a 4th year Ph.D. student at Simon Fraser University, under the supervision of Prof. Hao (Richard) Zhang. He received his Master’s degree from Simon Fraser University in 2019, and Bachelor’s degree from Shanghai Jiao Tong University in 2017. He won best student paper award at CVPR 2020, and received Google PhD Fellowship in 2021. His research interest is in Computer Graphics with a specialty in Geometric Modeling and Machine Learning.
个人主页：https://czq142857.github.io/
主持人简介：
崔兆鹏，浙江大学计算机学院CAD&CG国家重点实验室“百人计划”研究员、博士生导师。2017年在加拿大西蒙弗雷泽大学获得博士学位。2017年至2020年在瑞士苏黎世联邦理工学院计算机视觉和几何实验室任高级研究员。研究方向为三维计算机视觉，主要从事基于视觉信息的三维感知和理解，具体包括三维重建、运动恢复结构、多视角立体几何、三维场景理解、同时定位与地图构建、视频图像编辑等。近年来在计算机视觉、机器人、计算机图形学、机器学习等领域的顶级期刊和会议（TPAMI、CVPR、ICCV、SIGGRAPH、NeurIPS、ICRA、IROS）上发表论文40余篇，曾获ICRA 2020 最佳机器视觉论文提名和IROS 2021最佳安全、安保和救援机器人论文提名。
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接：http://webinar.games-cn.org
