GAMES Webinar 2022 – 237期(高效绘制) | Xihao Fu(Nanjing University)，Hanggao Xin(Tsinghua University)
【GAMES Webinar 2022-237期】(渲染专题-高效绘制)
报告嘉宾：Xihao Fu(Nanjing University)
报告题目：ExtraNet: Real-time Extrapolated Rendering for Low-latency Temporal Supersampling
Both the frame rate and the latency are crucial to the performance of real-time rendering applications such as video games. Spatial supersampling methods, such as the Deep Learning SuperSampling (DLSS), have been proven successful at decreasing the rendering time of each frame by rendering at a lower resolution. But temporal supersampling methods that directly aim at producing more frames on the fly are still not practically available. This work presents ExtraNet, an efficient neural network that predicts accurate shading results on an extrapolated frame, to minimize both the performance overhead and the latency. With the help of the rendered auxiliary geometry buffers of the extrapolated frame, and the temporally reliable motion vectors, ExtraNet can perform two tasks simultaneously: irradiance in-painting for regions that cannot find historical correspondences, and accurate ghosting free shading prediction for regions where temporal information is available. In addition, the lightweight design of ExtraNet guarantees fast inference. As a result, ExtraNet is able to produce plausibly extrapolated frames without easily noticeable artifacts, delivering a 1.5× to near 2× increase in frame rates with minimized latency in practice.
Xihao Fu received his M. S. degree from Department of Computer Science and Technology, Nanjing University in 2022, supervised by Jie Guo. He received his bachelor degree from School of Mathematics and Systems Science, Beihang University in 2019. His research mainly focuses on real-time rendering.
报告嘉宾：Hanggao Xin(Tsinghua University)
报告题目：Fast and Accurate Spherical Harmonics Products
Spherical Harmonics (SH) have been proven as a powerful tool for rendering, especially in real-time applications such as Precomputed Radiance Transfer (PRT). Spherical harmonics are orthonormal basis functions and are efficient in computing dot products. However, computations of triple product and multiple product operations are often the bottlenecks that prevent moderately high-frequency use of spherical harmonics. Specifically, state-of-the-art methods for accurate SH triple products of order 𝑛 have a time complexity of 𝑂(𝑛^5), which is a heavy burden for most real-time applications. Even worse, a brute-force way to compute 𝑘-multiple products would take 𝑂(𝑛^2𝑘) time. In this paper, we propose a fast and accurate method for spherical harmonics triple products with the time complexity of only 𝑂(𝑛^3), and further extend it for computing 𝑘-multiple products with the time complexity of 𝑂(𝑘𝑛^3 + 𝑘^2𝑛^2log(𝑘𝑛)). Our key insight is to conduct the triple and multiple products in the Fourier space, in which the multiplications can be performed much more efficiently. To our knowledge, our method is theoretically the fastest for accurate spherical harmonics triple and multiple products. And in practice, we demonstrate the efficiency of our method in rendering applications including mid-frequency relighting and shadow fields.
Hanggao Xin is a fourth-year Ph.D. student at Tsinghua University, advised by Prof. Shi-Min Hu and Prof. Shing-Tung Yau. He received his bachelor degree from Department of Computer Science and Technology, Tsinghua University in 2018. His research focuses on physically-based rendering rendering, real-time rendering and differentiable rendering.
吴鸿智，浙江大学计算机科学与技术学院教授、博导，获得国家优青基金资助。博士毕业于美国耶鲁大学。主要研究兴趣为高密度采集装备与可微分建模，研制了多套具有自主知识产权的高密度光源阵列采集装备，研究成果发表于ACM TOG/IEEE TVCG等CCF-A类期刊，合作出版了计算机图形学译著2部，主持了国家自然科学基金多个研究项目以及微软亚洲研究院合作项目。担任Chinagraph程序秘书长，中国图像图形学会国际合作与交流工作委员会秘书长、智能图形专委会委员，CCF CAD&CG专委会委员，以及EG、PG、EGSR、CAD/Graphics等多个国际会议的程序委员会委员。
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；