GAMES Webinar 2020 – 150期(海外专题) | Praneeth Chakravarthula (University of North Carolina at Chapel Hill), Edward (Shiqiu) Liu (NVIDIA Applied Deep Learning Research)
【GAMES Webinar 2020-150期】(海外专题)
报告嘉宾1：Praneeth Chakravarthula (University of North Carolina at Chapel Hill)
报告时间：2020年8月6号星期四早上10:00 – 10:45（北京时间）
报告题目：High resolution holographic image synthesis for future display eyeglasses
报告摘要：
This talk will present to the audience a new family of techniques for computer generated holography (CGH), collectively referred to as “Wirtinger Holography”, that promises unprecedented capabilities for future displays, including eyeglasses-style near-eye displays for augmented and virtual reality. CGH is often associated with noisy monocolor imagery with low contrast, making it impractical to use. While part of this is due to the severe limitations of the existing hardware, the current day CGH techniques are still at their infancy leading to modest holographic images. Wirtinger holography techniques overcome several of these challenges related to both hardware limitations as well as existing phase retrieval methods and result in superior quality holograms, making it one of the most promising techniques for holographic displays.
讲者简介：
Praneeth Chakravarthula is a graduate student at UNC Chapel Hill working with Prof. Henry Fuchs on next generation novel near-eye displays for virtual and augmented reality. His research interests lie at the intersection of optics, graphics, optimization and machine learning. Prior to joining UNC, Praneeth obtained his B.Tech and M.Tech degrees in Electrical Engineering, with a specialization in Signal Processing, all from IIT Madras, India. He has previously held research internship positions at Facebook Reality Labs, Microsoft Research Cambridge and NVIDIA Research. He was also a visiting researcher at the MIT Media Lab and NUS Singapore. Praneeth is a recipient of Best paper awards at ISMAR, IEEE VR, SPIE Photonics West and OSA Biophotonics and a Best in show award at SIGGRAPH Emerging Technologies.
讲者个人主页: https://www.cs.unc.edu/~cpk/
报告嘉宾2： Edward (Shiqiu) Liu (NVIDIA Applied Deep Learning Research)
报告时间：2020年8月6号星期四早上10:45 – 11:30（北京时间）
报告题目：DLSS 2.0 – Image Reconstruction for Real-Time Rendering with Deep learning
报告摘要：
In this talk, Edward Liu from NVIDIA Applied Deep Learning Research delves into the latest research progress on Deep Learning Super Sampling (DLSS), which uses deep learning and the NVIDIA Tensor Cores to reconstruct super sampled frames in real time. He discusses and demonstrates why scaling and image reconstruction for real-time rendering is an extremely challenging problem, and examines the cause of common artifacts produced by traditional up-sampling techniques. With this background, Edward then shows how the DLSS, deep learning-based reconstruction algorithm, achieves better image quality with less input samples than traditional techniques.
讲者简介：
Edward (Shiqiu) Liu is a Senior Research Scientist at NVIDIA Applied Deep Learning Research, where he currently explores the exciting application of deep learning in real-time graphics pipeline.
Edward has extensive experience in developing temporal coherence related techniques to improve rendering performance and quality. He is one of the key researchers behind several important technologies that are critical to next-gen real-time rendering, including DLSS 2.0 for image super resolution using deep learning and various spatio-temporal reconstruction algorithms for low sample count ray tracing. Edward is also a key contributor to the early research and prototyping of real-time ray tracing (RTX) in modern game engines.
讲者个人主页: http://behindthepixels.io/
主持人简介：
闫令琪博士，加州大学圣塔芭芭拉分校助理教授，于 2013 年获清华大学学士学位，2018 年获加州大学伯克利分校博士学位。他的主要研究方向是基于物理的真实感图形渲染及其相关的数学和物理理论，包括真实感材质观测和建模、离线和实时的光线追踪、信号的采样和重建、高效的光线传播和散射等。闫令琪在高度细致的真实感渲染方面的研究开创了下一代计算机图形学的研究方向, 在实时光线追踪方面的贡献直接推动了工业界的光线追踪 GPU 架构。闫令琪博士在 2018 年因其开创性研究被授予 C.V. Ramamoorthy 杰出科研奖，并于 2019 年获得 SIGGRAPH 最佳博士论文奖。他的科研成果还被直接应用于电影和游戏行业，曾帮助影片《猩球崛起3：终极之战》获得 2018 年奥斯卡最佳视觉效果奖提名，并在《狮子王2019》中的动物毛发渲染上得到广泛应用。
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
