Yuanming Hu 胡渊鸣
I graduated with honor from Tsinghua University (Yao class) in July 2017. I worked on deep learning and computer vision, during my internship with Stephen Lin at Microsoft Research Asia. My undergraduate thesis is on automatic photo post-processing using reinforcement learning and adversarial learning (presented at SIGGRAPH 2018). I completed my master thesis (The ChainQueen Differentiable Physical Simulator) with Wojciech Matusik in November 2018. My work has been partly supported by an Edwin Webster fellowship and a Snap Research fellowship.
Contact: yuanming _at_ mit.edu Github
My current research interests include ...
- High-performance systems for computer graphics:
- The Taichi programming language for high-performance sparse visual computing (main project since January 2019);
- DiffTaichi: Differentiable programming for physical simulation.
- Giga-Voxel Narrowband TopOpt: topology optimization of 1,040,875,347 voxels on a single computer with an MGPCG FEM solver and SPGrid;
- SIMD MLS-MPM: hand-optimized CPU MLS-MPM 14x faster than the previous state of the art.
- Physical simulation for VFX, machine learning, and robotics:
- Computational photography and deep learning:
- (07/2019) Welcome to our SIGGRAPH 2019 course On Hybrid Lagrangian-Eulerian Simulation Methods: Practical Notes and High-Performance Aspects (Thursday 3:45pm-5:15pm Room 408AB)! [Course Website]
- (07/2019) We have one programming language paper conditionally accepted to SIGGRAPH Asia 2019.
- (07/2019) MLS-MPM is featured on Two Minute Papers.
- (06/2019) ChainQueen is on the MIT CSAIL news.
- (05/2019) The code for our 1,040,875,347 voxel topology optimization is released.
- (04/2019) We will present the course On Hybrid Lagrangian-Eulerian Simulation Methods: Practical Notes and High-Performance Aspects at SIGGRAPH 2019.
- (03/2019) Our high-performance MLS-MPM with CPIC software (taichi_mpm) is now released under the commercially permissive MIT license (previously GPL).
- (02/2019) I am selected as one of the 2019 Snap Research Fellows.
- (01/2019) Our ChainQueen paper (differentiable MLS-MPM solver) is accepted by ICRA 2019 [Video].
- (11/2018) My #include <taichi> talk introduces tricks I used to amalgamate Taichi into a single header.
- (10/2018) Our 88-line MLS-MPM solver now supports all platforms with no external dependency. It has only 88 lines of essential code, real-time performance, and built-in UI for visualization. All these made it very suitable for learning and teaching MLS-MPM. [Visual result]
- (09/2018) Our differentiable MLS-MPM solver for soft robotics is now on Arxiv [Video].
- (08/2018) Our high-performance MLS-MPM solver with CPIC is open source. MLS-MPM can be implemented within 88 lines of code.
- (08/2018) We have two papers conditionally accepted to SIGGRAPH Asia 2018.
- (07/2018) I will talk 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).
- (06/2018) I will speak at the first event of Boston Computational Creativity group.
- (06/2018) We have one simulation paper accepted to SCA 2018.
- (05/2018) 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.
- (04/2018) My article about building a reusable infrastructure for computer graphics is on arXiv.
- (04/2018) We released our code for the CVPR 2017 paper "FC4 : Fully Convolutional Color Constancy with Confidence-weighted Pooling".
- (03/2018) We have one simulation paper conditionally accepted to SIGGRAPH 2018.
- (03/2018) The code for our Exposure project is now open-source.
- (02/2018) Our paper Exposure: A White-Box Photo Post-Processing Framework is accepted by ACM Transactions on Graphics. We will present it at SIGGRAPH 2018.
DiffTaichi: Differentiable Programming for Physical Simulation
arXiv 2019 [Code][Video]
Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan
Ragan-Kelley, Fredo Durand
The ChainQueen Differentiable Physics Engine
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
Workshop on Modeling the Physical World: Perception, Learning, and Control (Oral), NIPS 2018
Yuanming Hu, Jiancheng Liu*, Andrew Spielberg* (joint 2nd authors), Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu, Daniela Rus, Wojciech Matusik
Narrow-Band Topology Optimization on a Sparsely Populated Grid
ACM Transactions on Graphics, SIGGRAPH Asia 2018
Haixiang Liu*, Yuanming Hu* (joint first authors), Bo Zhu, Wojciech Matusik, Eftychios Sifakis
[Video] [Project Page & Code]
Deep Multispectral Painting Reproduction via Multi-layer, Custom-Ink Printing
ACM Transactions on Graphics, SIGGRAPH Asia 2018
Liang Shi, Vahid Babaei, Changil Kim, Michael Foshey, Yuanming Hu, Pitchaya Sitthi-Amorn, Szymon Rusinkiewicz, Wojciech Matusik
[Supplemental Document] [Multispectral Scans] [Uncompressed paper]
Exposure: A White-Box Photo Post-Processing Framework
ACM Transactions on Graphics, presented at SIGGRAPH 2018
Yuanming Hu, Hao He, Chenxi Xu, Baoyuan Wang, Stephen Lin
[Project Page & Code]
Ph.D. Student@Massachusetts Institute of Technology 2017.9-
Right now I am a Ph.D. student at MIT CSAIL. I work on computational photography, physical simulation, and high-performance graphics systems.
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).
Research Intern@Microsoft Research Asia 2016.9-2017.6
Computer vision research with Dr. Stephen Lin and Dr. Baoyuan Wang. We developed a novel color constancy algorithm that outperforms the previous state of the art with a 100-fold speed increase (CVPR 2017, oral), and a practical generative adversarial network (combined with reinforcement learning) that is capable of processing images with no resolution limits (ACM TOG, presented at SIGGRAPH 2018).
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.
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.
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