时间：11月22日（本周五）13:30-16:00

地点：信息楼计算机广场第一讨论室（研究生工位的小讨论室）

讨论班内容如下

1 报告人：王珏 Modern mobile Computational Photography - A Case Study （海天学者）

2 报告人：仲维 面向汽车自动/辅助驾驶的双目立体车载相机

诚挚邀请各位老师参加，并通知相关研究生参加。

讲座内容简介：

With the recent developments of mobile camera system, AI chipsets and deep learning methods, mobile computational photography has entered a new era, where powerful computational models work together with advanced hardware configurations to deliver new, exciting photography user experiences to consumers. In this talk, I will introduce a real example of modern mobile computational photography practice that we have worked on for the past year: Oppo Super Night Shot. I will introduce how we use latest deep learning techniques for image denoising and multi-frame alignment, and how to combine deep models with traditional algorithms to produce a complete pipeline that can be deployed in a real mobile device.

王珏博士简介：

Dr. Wang is a Senior Director of Megvii, leading a research team that focuses on transforming mobile user experience with AI. He received his BE and MS from Tsinghua University in Beijing, and his PhD from the University of Washington at Seattle. He was a Principal Scientist at Adobe Research before joining Megvii in 2017. He has published more than 100 research articles in top-tier academic journals and conferences in the areas of Computer Vision, Computer Graphics, Machine Learning and HCI, and holds more than 70 international patents.

Dr. Wang also has a respectable record of transferring advanced technologies into consumer products. His early work in grad school on Image Matting has been transferred into a commercial product called Silhouette that won 2019 Oscar technical award. At Adobe he has developed a dozen of release-defining features for Photoshop and After Effects such as Refine Edge, Shake Reduction, Warp Stabilizer and RotoBrush, etc.