Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Danfei Xu

Danfei Xu

Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control


Feb 28, 2021
Chen Wang, Rui Wang, Danfei Xu, Ajay Mandlekar, Li Fei-Fei, Silvio Savarese

Figure 1 for Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Figure 2 for Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Figure 3 for Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Figure 4 for Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
* First two authors contributed equally 
  Access Paper or Ask Questions

Human-in-the-Loop Imitation Learning using Remote Teleoperation


Dec 12, 2020
Ajay Mandlekar, Danfei Xu, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, Silvio Savarese

Figure 1 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 2 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 3 for Human-in-the-Loop Imitation Learning using Remote Teleoperation
Figure 4 for Human-in-the-Loop Imitation Learning using Remote Teleoperation

  Access Paper or Ask Questions

Deep Affordance Foresight: Planning Through What Can Be Done in the Future


Nov 17, 2020
Danfei Xu, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Figure 1 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 2 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 3 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Figure 4 for Deep Affordance Foresight: Planning Through What Can Be Done in the Future

  Access Paper or Ask Questions

Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations


Mar 13, 2020
Ajay Mandlekar, Danfei Xu, Roberto Martín-Martín, Silvio Savarese, Li Fei-Fei

Figure 1 for Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
Figure 2 for Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
Figure 3 for Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
Figure 4 for Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
* First two authors contributed equally 
  Access Paper or Ask Questions

Positive-Unlabeled Reward Learning


Nov 01, 2019
Danfei Xu, Misha Denil

Figure 1 for Positive-Unlabeled Reward Learning
Figure 2 for Positive-Unlabeled Reward Learning
Figure 3 for Positive-Unlabeled Reward Learning
Figure 4 for Positive-Unlabeled Reward Learning

  Access Paper or Ask Questions

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints


Oct 23, 2019
Chen Wang, Roberto Martín-Martín, Danfei Xu, Jun Lv, Cewu Lu, Li Fei-Fei, Silvio Savarese, Yuke Zhu

Figure 1 for 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
Figure 2 for 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
Figure 3 for 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
Figure 4 for 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

  Access Paper or Ask Questions

Regression Planning Networks


Sep 28, 2019
Danfei Xu, Roberto Martín-Martín, De-An Huang, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Figure 1 for Regression Planning Networks
Figure 2 for Regression Planning Networks
Figure 3 for Regression Planning Networks
Figure 4 for Regression Planning Networks
* Accepted at NeurIPS 2019 
  Access Paper or Ask Questions

Situational Fusion of Visual Representation for Visual Navigation


Aug 24, 2019
William B. Shen, Danfei Xu, Yuke Zhu, Leonidas J. Guibas, Li Fei-Fei, Silvio Savarese

Figure 1 for Situational Fusion of Visual Representation for Visual Navigation
Figure 2 for Situational Fusion of Visual Representation for Visual Navigation
Figure 3 for Situational Fusion of Visual Representation for Visual Navigation
Figure 4 for Situational Fusion of Visual Representation for Visual Navigation

  Access Paper or Ask Questions

Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning


Aug 16, 2019
De-An Huang, Danfei Xu, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei, Juan Carlos Niebles

Figure 1 for Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
Figure 2 for Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
Figure 3 for Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
Figure 4 for Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
* IROS 2019 
  Access Paper or Ask Questions

Procedure Planning in Instructional Videos


Jul 02, 2019
Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles

Figure 1 for Procedure Planning in Instructional Videos
Figure 2 for Procedure Planning in Instructional Videos
Figure 3 for Procedure Planning in Instructional Videos
Figure 4 for Procedure Planning in Instructional Videos
* 10 pages, 4 figures 
  Access Paper or Ask Questions

Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration


Mar 06, 2019
De-An Huang, Suraj Nair, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles

Figure 1 for Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
Figure 2 for Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
Figure 3 for Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
Figure 4 for Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
* CVPR 2019 
  Access Paper or Ask Questions

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion


Jan 15, 2019
Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martín-Martín, Cewu Lu, Li Fei-Fei, Silvio Savarese

Figure 1 for DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
Figure 2 for DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
Figure 3 for DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
Figure 4 for DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

  Access Paper or Ask Questions

PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation


Aug 25, 2018
Danfei Xu, Dragomir Anguelov, Ashesh Jain

Figure 1 for PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Figure 2 for PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Figure 3 for PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Figure 4 for PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
* CVPR 2018 
  Access Paper or Ask Questions

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks


Mar 14, 2018
Danfei Xu, Suraj Nair, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese

Figure 1 for Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
Figure 2 for Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
Figure 3 for Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
Figure 4 for Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
* ICRA 2018 
  Access Paper or Ask Questions

Scene Graph Generation by Iterative Message Passing


Apr 12, 2017
Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei

Figure 1 for Scene Graph Generation by Iterative Message Passing
Figure 2 for Scene Graph Generation by Iterative Message Passing
Figure 3 for Scene Graph Generation by Iterative Message Passing
Figure 4 for Scene Graph Generation by Iterative Message Passing
* CVPR 2017 
  Access Paper or Ask Questions

Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects


Jul 15, 2016
Yinxiao Li, Yan Wang, Yonghao Yue, Danfei Xu, Michael Case, Shih-Fu Chang, Eitan Grinspun, Peter Allen

Figure 1 for Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
Figure 2 for Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
Figure 3 for Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
Figure 4 for Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects
* 21 pages, 27 figures 
  Access Paper or Ask Questions

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction


Apr 02, 2016
Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese

Figure 1 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 2 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 3 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
Figure 4 for 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
* Appendix can be found at http://cvgl.stanford.edu/papers/choy_16_appendix.pdf 
  Access Paper or Ask Questions

Multi-Sensor Surface Analysis for Robotic Ironing


Feb 16, 2016
Yinxiao Li, Xiuhan Hu, Danfei Xu, Yonghao Yue, Eitan Grinspun, Peter Allen

Figure 1 for Multi-Sensor Surface Analysis for Robotic Ironing
Figure 2 for Multi-Sensor Surface Analysis for Robotic Ironing
Figure 3 for Multi-Sensor Surface Analysis for Robotic Ironing
Figure 4 for Multi-Sensor Surface Analysis for Robotic Ironing
* 7 pages, 6 figures in IEEE International Conference on Robotics and Automation (ICRA), Stockholm, May 2016 
  Access Paper or Ask Questions

Folding Deformable Objects using Predictive Simulation and Trajectory Optimization


Dec 22, 2015
Yinxiao Li, Yonghao Yue, Danfei Xu, Eitan Grinspun, Peter Allen

Figure 1 for Folding Deformable Objects using Predictive Simulation and Trajectory Optimization
Figure 2 for Folding Deformable Objects using Predictive Simulation and Trajectory Optimization
Figure 3 for Folding Deformable Objects using Predictive Simulation and Trajectory Optimization
Figure 4 for Folding Deformable Objects using Predictive Simulation and Trajectory Optimization
* 8 pages, 9 figures, Proceedings of IROS 2015 
  Access Paper or Ask Questions