Danfei Xu

I am currently a CS Ph.D. candidate at Stanford University. I am advised by Silvio Savarese and Fei-Fei Li who co-lead the Stanford Vision and Learning Lab. My recent research interests are robot learning and 3D computer vision. My research goal is to bridge the gap between perception and control for robots.

I also have broad interests in applied areas such as autonomous driving and assistive robots. I have worked at ZOOX, Autodesk Research, CMU RI, and SynTouch on various projects. Before joining Stanford, I recevied my B.S. from Columbia Univeristy, where I worked on deformable object manipulation and won the 2015 CRA Outstanding Undergraduate Researcher Award.

Email  /  Google Scholar  /  Github  /  Twitter

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
Danfei Xu*, Suraj Nair*, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese
ICRA, 2018


Neural Task Programming (NTP) is a meta-learning framework that learns to generate robot-executable neural programs from task demonstration video.

PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Danfei Xu, Ashesh Jain, Dragomir Anguelov
CVPR, 2018 (to appear)

PointFusion performs 3D object detection by fusing raw point cloud and RGB image and predicting 3D object bounding boxes end-to-end. PointFusion works both in outdoor urban driving scenarios and indoor scenes.

Scene Graph Generation by Iterative Message Passing
Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei
CVPR, 2017

[website] [code]

We propose an end-to-end model that jointly infers object category, location, and relationships. The model learns to iteratively improve its prediction by passing messages on a scene graph.

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Christopher B. Choy, Danfei Xu*, JunYoung Gwak*, Silvio Savarese
ECCV, 2016

[website] [code]

We propose an end-to-end 3D reconstruction model that unifies single- and multi-view reconstruction.

Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
Yinxiao Li , Yan Wang , Yonghao Yue , Danfei Xu, Michael Case , Shih-Fu Chang , Eitan Grinspun , Peter K. Allen


Deformable object manipulation with an application of personal assitive robot.

This is the journal paper of our "laundry robot" series:
ICRA 2015
IROS 2015
ICRA 2016

Topometric localization on a road network
Danfei Xu, Hernan Badino, Daniel Huber
IROS, 2015

Vision-based localization on a probabilistic road network.

Tactile identification of objects using Bayesian exploration
Danfei Xu, Gerald E. Loebm Jeremy Fishel
ICRA, 2013

Object classification using multi-modal tactile sensing.

Template source