GAMES Webinar 2019 – 99期(SIGGRAPH 2019 报告) | 张心欣(北京电影学院),高端(清华大学)

【GAMES Webinar 2019-99期】


报告时间:2019年6月20日 晚8:00-8:45(北京时间)
主持人:任博 ,南开大学(个人主页:
报告题目:Efficient and Conservative Fluids Using Bidirectional Mapping


In this paper, we introduce BiMocq2, an unconditionally stable, pure Eulerian-based advection scheme to efficiently preserve the advection accuracy of all physical quantities for long-term fluid simulations. Our approach is built upon the method of characteristic mapping (MCM).

Instead of the costly evaluation of the temporal charac-teristic integral, we evolve the mapping function itself by solving an  advec-tion equation for the mappings.

Dualmesh characteristics (DMC) method is adopted to more accurately updatethe  mapping.  Furthermore, to avoid visual artifacts like instant blur and temporal inconsistency introduced by re-initialization, we introduce multi-level mapping and back and forth error compensation.

We conduct comprehensive 2D and 3D benchmark experiments to compare against alternative advection schemes. In particular, for the vortical flow and level set experiments, our method outperforms almost all state-of-arthybrid schemes, including FLIP, PolyPic and Particle-Level-Set, at the cost of only two Semi-Lagrangian advections. Additionally, our method does not rely on the particle-grid transfer operations, leading to a highly paralleliz-able pipeline. As a result, more than 45×performance acceleration can beachieved via even a straightforward porting of the code from CPU to GPU.


张心欣博士毕业于英属哥伦比亚大学, 研究领域为计算流体仿真,高性能计算以及数值线性代数, 期间参与皮克斯、维塔数码等特效工作室研发工作, 并因指环王3霍比特人中的研发工作得Screen Credits。 毕业后加入创业公司Lytro, 其后被谷歌收购, 现于北京电影学院高精尖未来影像创新中心全职研究员, 参与开源软件OpenSubdiv,开源并发式流体解算软件以及并发式半代数多尺度网格泊松方程求解器,被多所科研机构以及SIGGRAPH论文直接使用。




报告时间:2019年6月20日 晚8:45-9:30(北京时间)
主持人:任博 ,南开大学(个人主页:
报告题目:Deep Inverse Rendering for High-resolution SVBRDF Estimation from an Arbitrary Number of Images


We present a unified deep inverse rendering framework for estimating the spatially-varying appearance properties of a planar exemplar from an arbitrary number of input photographs, ranging from just a single photograph to many photographs. The precision of the estimated appearance scales from plausible when the input photographs fails to capture all the reflectance information, to accurate for large input sets. In this talk, we will introduce the structure of our neural network and apply this model to optimization framework, and we demonstrate and evaluate our deep inverse rendering solution on a wide variety of publicly available datasets.


I am a second-year Ph.D. student at Tsinghua University, advised by Prof. Kun Xu. I received my bachelor degree from Department of Computer Science and Technology, Nanjing University in 2017. My research interests include: appearance modeling, physically-based rendering and real-time rendering.



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...