Lifan Wu

I am Lifan Wu, a third year PhD student at University of California, San Diego. My advisor is Prof. Ravi Ramamoorthi. I graduated from Tsinghua University in July 2015.

My research interest is physically based rendering, including sparse sampling and reconstruction of visual signals, realistic appearance modeling, and light transport. At Tsinghua, I worked at Graphics and Geometric Computing Group, advised by Prof. Kun Xu. In summer 2014, I worked as a research intern at Washington University in St. Louis, advised by Prof. Tao Ju.

Email: winmad.wlf [at] gmail [dot] com

Curriculum Vitae




Multiple Axis-Aligned Filters for Rendering of Combined Distribution Effects
Lifan Wu, Ling-Qi Yan, Alexandr Kuznetsov, Ravi Ramamoorthi
Computer Graphics Forum (EGSR 2017), June 2017
[Paper] [Slides] [Video]


Downsampling Scattering Parameters for Rendering Anisotropic Media
Shuang Zhao*, Lifan Wu*, Fredo Durand, Ravi Ramamoorthi
(* Joint first authors)
ACM Transactions on Graphics (SIGGRAPH Asia 2016), Nov. 2016
[Project] [Paper] [Slides] [Video] [Code & Data]



Intermediate Path Tracing and Merging
Working with Fujun Luan, Weilun Sun, Kun Xu
(Inspired by Vertex Connection and Merging. Using intermediate paths and a path merging graph to increase path samples and improve path reusing)


PointContour: Interactive Surface Reconstruction on Point Cloud
Working with Yixin Zhuang, Ming Zou, Zhao Fu, Nathan Carr, Tao Ju
(A semi-automatic tool to generate surfaces via input point cloud and sketches drawn by users)


Anisotropic Density Estimation for Photon Mapping
Fujun Luan, Lifan Wu, Kun Xu
Accepted to Computational Visual Media 2015
(An anisotropic filtering kernel for photon density estimation to handle anisotropic BRDFs)


Seam Carving: Content-Aware Image Resizing
Course project of General Computer Science
(Reproduced an adaptive image resizing algorithm, based on SIGGRAPH 2007 paper Seam Carving)


Mesh Simplification
Course project of Fundamentals of Computer Graphics
(Implemented a mesh simplification algorithm using quadratic error metric)