GAMES Webinar 2020 – 160期(绘制专题) | Yezi Zhao(Shandong University), Jie Guo(Nanjing University)

【GAMES Webinar 2020-160期】(绘制专题)

报告嘉宾1:Yezi Zhao(Shandong University)


报告题目:Joint SVBRDF Recovery and Synthesis From a Single Image using an Unsupervised Generative Adversarial Network


We want to recreate spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a single image. Producing these SVBRDFs from single images will allow designers to incorporate many new materials in their virtual scenes, increasing their realism. Existing algorithms can produce high-quality SVBRDFs with single or few input photographs using supervised deep learning. The learning step relies on a huge dataset with both input photographs and the ground truth SVBRDF maps. This is a weakness as ground truth maps are not easy to acquire. For practical use, it is also important to produce large SVBRDF maps. Existing algorithms rely on a separate texture synthesis step to generate these large maps, which leads to the loss of consistency between generated SVBRDF maps. In this paper, we address both issues simultaneously. We present an unsupervised generative adversarial neural network that addresses both SVBRDF capture from a single image and synthesis at the same time. From a low-resolution input image, we generate a large resolution SVBRDF, much larger than the input images. We train a generative adversarial network (GAN) to get SVBRDF maps, which have both a large spatial extent and detailed texels. Each input for our method requires individual training, which costs about 3 hours.



报告嘉宾2:Jie Guo (Nanjing University)


报告题目:DeepBRDF: A Deep Representation for Manipulating Measured BRDF


Effective compression of densely sampled BRDF measurements is critical for many graphical or vision applications. In this paper, we present DeepBRDF, a deep-learning-based representation that can significantly reduce the dimensionality of measured BRDFs while enjoying high quality of recovery. We consider each measured BRDF as a sequence of image slices and design a deep autoencoder with a masked L2 loss to discover a nonlinear low-dimensional latent space of the high-dimensional input data. Thorough experiments verify that the proposed method clearly outperforms PCA-based strategies in BRDF data compression and is more robust. We demonstrate the effectiveness of DeepBRDF with two applications. For BRDF editing, we can easily create a new BRDF by navigating on the low-dimensional manifold of DeepBRDF, guaranteeing smooth transitions and high physical plausibility. For BRDF recovery, we design another deep neural network to automatically generate the full BRDF data from a single input image. Aided by our DeepBRDF learned from real-world materials, a wide range of reflectance behaviors can be recovered with high accuracy.


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.




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;

You may also like...