I am a senior research scientist at Apple (Seattle). I work on 3D reconstruction and real-time rendering for AR/VR applications, and more broadly computer vision, machine learning. Some of the research topics I’ve worked on include neural rendering, depth estimation, generative neural networks, and self-supervised learning.

I finished my Ph.D. in Autonomous Systems at Massachusetts Institute of Technology in 2019. Prior to that, I obtained my bachelor’s degree in Computer Engineering from Hong Kong University of Science and Technology in 2013.

Publications

RetrievalFuse: Neural 3D Scene Reconstruction with a Database
Yawar Siddiqui, Justus Thies, ‪Fangchang Ma, ‪Qi Shan, Matthias Nießner, Angela Dai
ICCV 2021 [pdf] [video]
Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera
Fangchang Ma, Guilherme Venturelli Cavalheiro, Sertac Karaman
ICRA 2019 [pdf] [code] [video]
FastDepth: Fast Monocular Depth Estimation on Embedded Systems
Diana Wofk*, Fangchang Ma*, Tien-Ju Yang, Sertac Karaman, Vivienne Sze
ICRA 2019 [pdf] [code] [webpage] [video]
Invertibility of Convolutional Generative Networks from Partial Measurements
Fangchang Ma, Ulas Ayaz, Sertac Karaman
NeurIPS 2018 [pdf] [supplementary] [code]
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
Fangchang Ma, Sertac Karaman
ICRA 2018 [pdf] [video] [pytorch code] [torch code]
Sparse Depth Sensing for Resource-Constrained Robots
Fangchang Ma, Luca Carlone, Ulas Ayaz, Sertac Karaman
IROS 2016 & IJRR [pdf] [code] [video]
On Sensing, Agility, and Computation Requirements for a Data-gathering Vehicle
Fangchang Ma, Sertac Karaman
WAFR 2014 [pdf]
Velocity estimator via fusing inertial measurements and multiple feature correspondences from a single camera
Guyue Zhou, Fangchang Ma, Zexiang Li, Tao Wang
ROBIO 2013 [pdf]

Service

Conference Reviewer: NeurIPS, ICLR, ICRA, IROS
Journal Reviewer: TPAMI, Pattern Recognition Letters, IJRR, RA-L, RAM, IEEE Sensors Journal, Unmanned Systems