About me

Page
DSC03406_cropped_small

Yuanming Hu          胡渊鸣

I am a first-year Ph.D. student at MIT EECS, supported by the Edwin Webster Graduate Fellowship.

Currently, my major research interest is computer graphics (physically based simulation, computational photography, and rendering). I worked on deep learning and computer vision, during my internship with Dr. Stephen Lin at Microsoft Research Asia.

I graduated with honor from Tsinghua University (Yao class) in July 2017. My undergraduate thesis is on automatic photo post-processing using reinforcement learning and adversarial learning (to be presented at SIGGRAPH 2018).

Email: yuanming _at_ mit.edu            Github     LinkedIn

News

  • (2018.7) I will talk (in Chinese) at GAMES: Graphics And Mixed Environment Seminar about our recent four projects (July 12 8:45pm: MLS-MPM-CPIC, AysncMPM [Slides]; July 19 8:45pm: Exposure, Taichi).
  • (2018.6) I will speak at the first event of Boston Computational Creativity group.
  • (2018.6) We have one simulation paper accepted to SCA 2018.
  • (2018.5) I will give the talk "From TensorFlow to Taichi: A GAN for Computational Photography, a Scheme for Physical Simulation, and a Library for Computer Graphics" at MIT CSAIL. Slides available upon request.
  • (2018.4) My article about building a reusable infrastructure for computer graphics is on arXiv.
  • (2018.4) We released our code for the CVPR 2017 paper "FC4 : Fully Convolutional Color Constancy with Confidence-weighted Pooling".
  • (2018.3) We have one simulation paper conditionally accepted to SIGGRAPH 2018, where I will present two papers.
  • (2018.3) The code for our Exposure project is now open-source.
  • (2018.2) Our paper Exposure: A White-Box Photo Post-Processing Framework is accepted by ACM Transactions on Graphics. I will present it at SIGGRAPH 2018.
  • ...

Publications

SCA & CGF 2018

Video

Code coming soon.

ACM Transactions on Graphics
SIGGRAPH 2018
Project Page & Code

An Asynchronous Material Point Method
Yuanming Hu*, Yu Fang* (joint first authors)

SIGGRAPH 2017, Poster

Research Experience

Ph.D. Student@Massachusetts Institute of Technology 2017.9-
I am now a Ph.D. student at the Computational Fabrication Group, mentored by Prof. Wojciech Matusik. I work on high-performance numerical simulation for computational fabrication and automatic discovery of microstructures.

mit

Visiting Student@The University of Pennsylvania 2017.7-2017.8
I visited Prof. Chenfanfu Jiang during summer 2017. We developed a new material point method that is faster and supports cutting and rigid-body coupling (SIGGRAPH 2018).

penn

Undergraduate Visiting Researcher@Stanford University 2016.6-2016.8
With Prof. Ron Fedkiw, I developed a novel line segment based reconstruction algorithm for fine tree details where previous methods do not perform well.

stanford

Internship Student@The University of Tokyo 2016.3-2016.6
Computer graphics research (physically based animation and rendering) with Prof. Seiichi Koshizuka and Prof. Toshiya Hachisuka. I implemented 10+ graphics papers during this internship and developed an initial version of Taichi, an open-source computer graphics library.

utokyo

Skills

Programming Languages:

        Good at       C++ 14/11, Python 3/2
        Capable of  CUDA, GLSL, Java, CoffeeScript/JavaScript, Mathematica, Haskell, HTML/CSS, Ruby, Bash

Tools: ssh, Vim, Git, TensorFlow, OpenGL, Qt, LaTeX, CMake, Visual Studio, CLion, tmux

(Natural) Languages: Chinese (native), English

        TOEFL: 112/120 (speaking 26)

Programming Contests

Asia-Pacific Informatics Olympiad 2012, China District

China National Olympiad in Informatics 2012

ACM-ICPC Asia Changsha Regional Contest 2013, with my team

ACM-ICPC Asia Shanghai Regional Contest 2014, with my team

China National Olympiad in Informatics 2014

Gold Medal, 1st / 450

Gold Medal, 13th / 350

Gold Medal, 3rd / 200

Gold Medal, 5th / 250

Problem Setter

Academic Services

IEEE Transactions on Image Processing, Reviewer

ACM SIGGRAPH Asia 2018, Reviewer

Hobbies

Photography, graphic design, animated films, creating and destroying everything in my physically based simulators