GAMES Webinar 2020 – 131期(绘制专题) |Jie Guo(Nanjing University), Bing Xu(Kujiale.com)

【GAMES Webinar 2020-131期】(绘制专题)

报告嘉宾1：Jie Guo, Nanjing University

报告时间：2020年3月19日 晚上8:00-8:45（北京时间）

报告题目：GradNet: Unsupervised Deep Screened Poisson Reconstruction for Gradient-Domain Rendering

报告摘要：

Monte Carlo (MC) methods for light transport simulation are flexible and general but typically suffer from high variance and slow convergence. Gradient-domain rendering alleviates this problem by additionally generating image gradients and reformulating rendering as a screened Poisson image reconstruction problem. To improve the quality and performance of the reconstruction, we propose a novel and practical deep learning based approach. The core of our approach is a multi-branch auto-encoder, termed GradNet, which end-to-end learns a mapping from a noisy input image and its corresponding image gradients to a high-quality image with low variance. Once trained, our network is fast to evaluate and does not require manual parameter tweaking. Due to the difficulty in preparing ground-truth images for training, we design and train our network in a completely unsupervised manner by learning directly from the input data. This is the first solution incorporating unsupervised deep learning into the gradient-domain rendering framework.

讲者简介：

Jie Guo is currently an assistant professor at the State Key Lab for Novel Software Technology, Nanjing University. He received his doctoral degree in department of computer science and technology from Nanjing University in 2013. His research interests include physically-based rendering, appearance modeling and virtual reality.

讲者个人主页: http://118.25.137.210/

报告嘉宾2：Bing Xu, Kujiale.com

报告时间：2020年3月19日 晚上8:45-9:30（北京时间）

报告题目：Adversarial Monte Carlo Denoising with Conditioned Auxiliary Feature Modulation

报告摘要：

Denoising Monte Carlo rendering with a very low sample rate remains a major challenge in the photo-realistic rendering research. Many previous works, including regression-based and learning-based methods, have been explored to achieve better rendering quality with less computational cost. However, most of these methods rely on handcrafted optimization objectives, which lead to artifacts such as blurs and unfaithful details. This talk will show how adversarial training and better use of rendering side-products improve the denoising quality and discuss more backgrounds in the MC denoising problem domain.

讲者简介：

Bing Xu is a senior research engineer at ZJU-Kujiale Joint Lab of CG&AI in Kujiale.com, under supervision of Dr. Rui Tang and Prof.Rui Wang, where she mainly works on self-developed FF renderer. Her research interest is Computer Graphics with specialty in physically-based rendering.  Bing received her bachelor degree in the University of Hong Kong in 2016 and will start the Ph.D. journey in UCSD this year.

讲者个人主页: http://bingxu.tech/

主持人简介：

王锐，浙江大学CAD&CG国家重点实验室教授，博士生导师。主要研究方向为图形渲染理论、算法与框架，在复杂光场高效采样、实时渲染算法、渲染架构的自动优化等方面取得了一系列创新科研成果。详见：http://www.cad.zju.edu.cn/home/rwang。

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