Wei-Chiu Ma 馬惟九

Ph.D. Student
Deptartment of Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Email: weichium [at] mit.edu

About Me

I am a Ph.D. student at MIT, advised by Antonio Torralba (aka the Great Torralba). My general research interest lies in computer vision and machine learning.

I also work closely with Raquel Urtasun at Uber ATG Toronto on self-driving problems.

Previously, I completed my M.S. in Robotics at Carnegie Mellon University (CMU) where I was advised by Kris M. Kitani.


 

Recent News

  • NEW Oct. 2019: The source code of our real-time stereo algorithm is available now! Make sure to check out the amzaing differentiable PatchMatch module!
  • NEW Jul. 2019: Three papers accepted to ICCV 2019! Details coming soon!
  • NEW Jun. 2019: Our paper on light-weight localization is accepted to IROS 2019!
  • NEW Mar. 2019: Two papers (scene flow and road boundary extraction) accepted to CVPR 2019!
  • Jul. 2018: Our paper on Unsupervised Intrinsic Decomposition is accepted to ECCV 2018!
  • Mar. 2018: 3 papers accepted to CVPR 2018!
  • Apr. 2017: Our book chapter on Activity Forecasting is published! Check it out!
  • Mar. 2017: Our work (a game-theoretic approach to multi-agent activity forecasting) is accepted to CVPR 2017!
  • Jan. 2017: Our work (self-localization for autonomous vehicles) is accepted to ICRA 2017!
  • May. 2016: I graduated from CMU --- thanks Kris for all your support in the past two years!

 

Research Projects

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
Shivam Duggal, Shenlong Wang, Wei-Chiu Ma, Rui Hu, and Raquel Urtasun
IEEE International Conference on Computer Vision (ICCV), 2019.
[arXiv] [Code & Differentiable PatchMatch Module]

Real-time stereo estimation (62 ms) via Differentiable PatchMatch!

The Sound of Motions
Hang Zhao, Chuang Gan, Wei-Chiu Ma, and Antonio Torralba
IEEE International Conference on Computer Vision (ICCV), 2019.
[arXiv] [demon video]

DAG-Mapper: Learning to Map by Discovering Lane Topology
Namdar Homayounfar, Wei-Chiu Ma, Justin Liang, Xinyu Wu, Jack Fan, and Raquel Urtasun
IEEE International Conference on Computer Vision (ICCV), 2019.
[paper (coming soon)]

Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
Wei-Chiu Ma*, Ignacio Tartavull*, Ioan Andrei Bârsan*, Shenlong Wang*, Min Bai, Gellert Mattyus, Namdar Homayounfar, Shrinidhi Kowshika Lakshmikanth, Andrei Pokrovsky, Raquel Urtasun
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.
[arXiv preprint]

Deep Rigid Instance Scene Flow
Wei-Chiu Ma, Shenlong Wang, Rui Hu, Yuwen Xiong, and Raquel Urtasun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[project page][arXiv preprint] [paper + supp. material (uncompressed)]
[see how GN solver improves performance]

Deep structured scene flow model that rank 1st on KITTI Scene Flow Benchmark.
Faster than prior art by 800 times.

Convolutional Recurrent Network for Road Boundary Extraction
Justin Liang*, Namdar Homayounfar*, Wei-Chiu Ma, Shenlong Wang, and Raquel Urtasun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[paper (coming soon)]

Single Image Intrinsic Decomposition without a Single Intrinsic Image
Wei-Chiu Ma, Hang Chu, Bolei Zhou, Raquel Urtasun, and Antonio Torralba
European Conference on Computer Vision (ECCV), 2018.
[paper]

Deep Parametric Continuous Convolutional Neural Networks
Shenlong Wang*, Simon Suo*, Wei-Chiu Ma, Andrei Pokrovsky, and Raquel Urtasun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Spotlight Presentation (accpetance rate: 6.7%)
[paper]

SurfConv: Bridging 3D and 2D Convolution for RGBD Images
Hang Chu, Wei-Chiu Ma, Kaustav Kundu, Raquel Urtasun, and Sanja Fidler
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[paper] [code]

Hierarchical Recurrent Attention Networks for Structured Online Maps
Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, and Raquel Urtasun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[paper] [supplmentary material (available upon request)]

Activity Forecasting: An Invitation to Predictive Perception
Kris M. Kitani, De-An Huang, and Wei-Chiu Ma
Book: Group and Crowd Behavior for Computer Vision. Chapter 12, 2017.
[preprint]

Find Your Way by Observing the Sun and Other Semantic Cues
Wei-Chiu Ma, Shenlong Wang, Marcus A. Brubaker, Sanja Fidler, and Raquel Urtasun
IEEE Conference on Robotics and Automation (ICRA), 2017.
[arXiv preprint] [demo video]

Forecasting Interactive Dynamics of Pedestrians with Fictitious Play
Wei-Chiu Ma, De-An Huang, Namhoon Lee, and Kris M. Kitani
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[arXiv preprint] [supplmentary material]

How Do We Use Our Hands? Discovering a Diverse Set of Common Grasps
De-An Huang, Wei-Chiu. Ma*, Minghuan Ma*, and K. M. Kitani (*=equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[paper]

Recognizing Hand-Object Interactions in Wearable Camera Videos
Tatsuya Ishihara, Kris M. Kitani, Wei-Chiu Ma, Hironobu Takagi, Chieko Asakawa
IEEE International Conference on Image Processing (ICIP), 2015.
[paper]

Novel traffic signal timing adjustment strategy based on Genetic Algorithm
Wei-Chiu Ma*, Hsiao-Yu Tung*, and Tian-Li Yu (*=equal contribution)
IEEE Congress on Evolutionary Computation (CEC), 2014.
Oral Presentation
[paper]

TDTOS: T-Shirt Design and Try On System
Wei-Chiu Ma*, Chen-Yu Hsu*, Chi-Hsien Yen*, and Shao-Yi Chien (*=equal contribution)
Asia-Pacific Workshop on FPGA Applications, 2012.
Oral Presentation (accpetance rate: 4.8%)
Best Application Award
[demo video]