Duan Gao (高端)

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.

Publications

Deep Inverse Rendering for High-resolution SVBRDF Estimation from an Arbitrary Number of Images

Duan Gao*, Xiao Li*, Yue Dong, Pieter Peers, Kun Xu, Xin Tong (* Equal contribution)
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2019)

In this paper we present a unifed 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. A key distinguishing feature of our framework is that it directly optimizes for the appearance parameters in a latent embedded space of spatially-varying appearance, such that no handcrafted heuristics are needed to regularize the optimization. This latent embedding is learned through a fully convolutional auto-encoder that has been designed to regularize the optimization. Our framework not only supports an arbitrary number of input photographs, but also at high resolution. We demonstrate and evaluate our deep inverse rendering solution on a wide variety of publicly available datasets.

Experience

- Research intern@Tecent AI Lab, 2019.7-2019.8

3D face related research with Dr. Haozhi Huang


- Research intern@Microsoft Research Asia, Internet Graphics Group 2018.8-2019.5

Appearance modeling research with Dr. Yue Dong and Dr. Xin Tong.


- Research intern@Megvii(Face++) 2017.7-2017.9

Facial recovery and rendering research with Dr. Liqian Ma.

Projects

Elegans Renderer
(Coming soon)

Physically based renderer. Supports multiple BRDF model and lighting models.

Smoke Simulation

Smoke simulation based on the paper “Visual Simulation of Smoke“

Face Relighting

3D face reconstruction from a single image and face relighting.“

BlueNoise Generator

Generate blue noise image.

Knitting

Toy projects: knitting by code.

Misc

Program languages : C/C++, Python, Java, OpenGL

Software : Git, LaTex, TensorFlow

Hobbies: : Reading, playing badminton