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 Shuran Song

Shuran Song

Google, Columbia University

Learning to See before Learning to Act: Visual Pre-training for Manipulation


Jul 01, 2021
Lin Yen-Chen, Andy Zeng, Shuran Song, Phillip Isola, Tsung-Yi Lin

Figure 1 for Learning to See before Learning to Act: Visual Pre-training for Manipulation
Figure 2 for Learning to See before Learning to Act: Visual Pre-training for Manipulation
Figure 3 for Learning to See before Learning to Act: Visual Pre-training for Manipulation
Figure 4 for Learning to See before Learning to Act: Visual Pre-training for Manipulation
* Accepted to ICRA 2020. Porject page: http://yenchenlin.me/vision2action/ 
  Access Paper or Ask Questions

Visual Perspective Taking for Opponent Behavior Modeling


May 11, 2021
Boyuan Chen, Yuhang Hu, Robert Kwiatkowski, Shuran Song, Hod Lipson

Figure 1 for Visual Perspective Taking for Opponent Behavior Modeling
Figure 2 for Visual Perspective Taking for Opponent Behavior Modeling
Figure 3 for Visual Perspective Taking for Opponent Behavior Modeling
Figure 4 for Visual Perspective Taking for Opponent Behavior Modeling
* ICRA 2021. Website: http://www.cs.columbia.edu/~bchen/vpttob/ 
  Access Paper or Ask Questions

FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding


May 08, 2021
Huy Ha, Shuran Song

Figure 1 for FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
Figure 2 for FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
Figure 3 for FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
Figure 4 for FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
* 9 pages, 6 figures 
  Access Paper or Ask Questions

Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery


May 03, 2021
Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song

Figure 1 for Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
Figure 2 for Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
Figure 3 for Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
Figure 4 for Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
* 16 pages, 16 figures 
  Access Paper or Ask Questions

GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion


Apr 12, 2021
Cheng Chi, Shuran Song

Figure 1 for GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
Figure 2 for GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
Figure 3 for GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
Figure 4 for GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion

  Access Paper or Ask Questions

Spatial Intention Maps for Multi-Agent Mobile Manipulation


Mar 23, 2021
Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Szymon Rusinkiewicz, Thomas Funkhouser

Figure 1 for Spatial Intention Maps for Multi-Agent Mobile Manipulation
Figure 2 for Spatial Intention Maps for Multi-Agent Mobile Manipulation
Figure 3 for Spatial Intention Maps for Multi-Agent Mobile Manipulation
Figure 4 for Spatial Intention Maps for Multi-Agent Mobile Manipulation
* To appear at IEEE International Conference on Robotics and Automation (ICRA), 2021. Project page: https://spatial-intention-maps.cs.princeton.edu/ 
  Access Paper or Ask Questions

Dynamic Grasping with Reachability and Motion Awareness


Mar 18, 2021
Iretiayo Akinola, Jingxi Xu, Shuran Song, Peter K. Allen

Figure 1 for Dynamic Grasping with Reachability and Motion Awareness
Figure 2 for Dynamic Grasping with Reachability and Motion Awareness
Figure 3 for Dynamic Grasping with Reachability and Motion Awareness
Figure 4 for Dynamic Grasping with Reachability and Motion Awareness

  Access Paper or Ask Questions

SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation


Dec 08, 2020
Yiqing Liang, Boyuan Chen, Shuran Song

Figure 1 for SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
Figure 2 for SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
Figure 3 for SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
Figure 4 for SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation

  Access Paper or Ask Questions

Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop


Dec 07, 2020
Sebastian Höfer, Kostas Bekris, Ankur Handa, Juan Camilo Gamboa, Florian Golemo, Melissa Mozifian, Chris Atkeson, Dieter Fox, Ken Goldberg, John Leonard, C. Karen Liu, Jan Peters, Shuran Song, Peter Welinder, Martha White

Figure 1 for Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop
* Summary of the "2nd Workshop on Closing the Reality Gap in Sim2Real Transfer for Robotics" held in conjunction with "Robotics: Science and System 2020". Website: https://sim2real.github.io/ 
  Access Paper or Ask Questions

AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy


Dec 03, 2020
Zhenjia Xu, Beichun Qi, Shubham Agrawal, Shuran Song

Figure 1 for AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
Figure 2 for AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
Figure 3 for AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
Figure 4 for AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
* Project page: https://adagrasp.cs.columbia.edu 
  Access Paper or Ask Questions

Fit2Form: 3D Generative Model for Robot Gripper Form Design


Nov 12, 2020
Huy Ha, Shubham Agrawal, Shuran Song

Figure 1 for Fit2Form: 3D Generative Model for Robot Gripper Form Design
Figure 2 for Fit2Form: 3D Generative Model for Robot Gripper Form Design
Figure 3 for Fit2Form: 3D Generative Model for Robot Gripper Form Design
Figure 4 for Fit2Form: 3D Generative Model for Robot Gripper Form Design
* Conference on Robot Learning 2020 
  Access Paper or Ask Questions

Learning a Decentralized Multi-arm Motion Planner


Nov 05, 2020
Huy Ha, Jingxi Xu, Shuran Song

Figure 1 for Learning a Decentralized Multi-arm Motion Planner
Figure 2 for Learning a Decentralized Multi-arm Motion Planner
Figure 3 for Learning a Decentralized Multi-arm Motion Planner
Figure 4 for Learning a Decentralized Multi-arm Motion Planner
* CoRL 2020 
  Access Paper or Ask Questions

Learning 3D Dynamic Scene Representations for Robot Manipulation


Nov 03, 2020
Zhenjia Xu, Zhanpeng He, Jiajun Wu, Shuran Song

Figure 1 for Learning 3D Dynamic Scene Representations for Robot Manipulation
Figure 2 for Learning 3D Dynamic Scene Representations for Robot Manipulation
Figure 3 for Learning 3D Dynamic Scene Representations for Robot Manipulation
Figure 4 for Learning 3D Dynamic Scene Representations for Robot Manipulation
* CoRL 2020. The first two authors contributed equally to this paper. Project page: https://dsr-net.cs.columbia.edu/ 
  Access Paper or Ask Questions

Multitask Learning Strengthens Adversarial Robustness


Jul 14, 2020
Chengzhi Mao, Amogh Gupta, Vikram Nitin, Baishakhi Ray, Shuran Song, Junfeng Yang, Carl Vondrick

Figure 1 for Multitask Learning Strengthens Adversarial Robustness
Figure 2 for Multitask Learning Strengthens Adversarial Robustness
Figure 3 for Multitask Learning Strengthens Adversarial Robustness
Figure 4 for Multitask Learning Strengthens Adversarial Robustness

  Access Paper or Ask Questions

Spatial Action Maps for Mobile Manipulation


Apr 20, 2020
Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Johnny Lee, Szymon Rusinkiewicz, Thomas Funkhouser

Figure 1 for Spatial Action Maps for Mobile Manipulation
Figure 2 for Spatial Action Maps for Mobile Manipulation
Figure 3 for Spatial Action Maps for Mobile Manipulation
Figure 4 for Spatial Action Maps for Mobile Manipulation
* Project webpage: https://spatial-action-maps.cs.princeton.edu 
  Access Paper or Ask Questions

Category-Level Articulated Object Pose Estimation


Dec 26, 2019
Xiaolong Li, He Wang, Li Yi, Leonidas Guibas, A. Lynn Abbott, Shuran Song

Figure 1 for Category-Level Articulated Object Pose Estimation
Figure 2 for Category-Level Articulated Object Pose Estimation
Figure 3 for Category-Level Articulated Object Pose Estimation
Figure 4 for Category-Level Articulated Object Pose Estimation
* 13 pages, 7 figures 
  Access Paper or Ask Questions

Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations


Dec 09, 2019
Shuran Song, Andy Zeng, Johnny Lee, Thomas Funkhouser

Figure 1 for Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
Figure 2 for Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
Figure 3 for Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
Figure 4 for Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
* Project Webpage https://graspinwild.cs.columbia.edu/ 
  Access Paper or Ask Questions

Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly


Oct 30, 2019
Kevin Zakka, Andy Zeng, Johnny Lee, Shuran Song

Figure 1 for Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
Figure 2 for Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
Figure 3 for Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
Figure 4 for Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
* Code, videos, and supplemental material are available at https://form2fit.github.io/ 
  Access Paper or Ask Questions

Visual Hide and Seek


Oct 15, 2019
Boyuan Chen, Shuran Song, Hod Lipson, Carl Vondrick

Figure 1 for Visual Hide and Seek
Figure 2 for Visual Hide and Seek
Figure 3 for Visual Hide and Seek
Figure 4 for Visual Hide and Seek
* 14 pages, 8 figures 
  Access Paper or Ask Questions

ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation


Oct 14, 2019
Shreeyak S. Sajjan, Matthew Moore, Mike Pan, Ganesh Nagaraja, Johnny Lee, Andy Zeng, Shuran Song

Figure 1 for ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
Figure 2 for ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
Figure 3 for ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
Figure 4 for ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
* Project Website: https://sites.google.com/view/cleargrasp, 13 pages, 13 figures, submitted to ICRA 
  Access Paper or Ask Questions

Neural Illumination: Lighting Prediction for Indoor Environments


Jun 18, 2019
Shuran Song, Thomas Funkhouser

Figure 1 for Neural Illumination: Lighting Prediction for Indoor Environments
Figure 2 for Neural Illumination: Lighting Prediction for Indoor Environments
Figure 3 for Neural Illumination: Lighting Prediction for Indoor Environments
Figure 4 for Neural Illumination: Lighting Prediction for Indoor Environments

  Access Paper or Ask Questions

DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions


Jun 11, 2019
Zhenjia Xu, Jiajun Wu, Andy Zeng, Joshua B. Tenenbaum, Shuran Song

Figure 1 for DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
Figure 2 for DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
Figure 3 for DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
Figure 4 for DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
* RSS 2019. Project page: http://zhenjiaxu.com/DensePhysNet 
  Access Paper or Ask Questions

TossingBot: Learning to Throw Arbitrary Objects with Residual Physics


Mar 27, 2019
Andy Zeng, Shuran Song, Johnny Lee, Alberto Rodriguez, Thomas Funkhouser

Figure 1 for TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
Figure 2 for TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
Figure 3 for TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
Figure 4 for TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
* Summary Video: https://youtu.be/f5Zn2Up2RjQ Project webpage: https://tossingbot.cs.princeton.edu 
  Access Paper or Ask Questions

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation


Jan 09, 2019
He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas

Figure 1 for Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
Figure 2 for Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
Figure 3 for Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
Figure 4 for Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

  Access Paper or Ask Questions

Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning


Sep 30, 2018
Andy Zeng, Shuran Song, Stefan Welker, Johnny Lee, Alberto Rodriguez, Thomas Funkhouser

Figure 1 for Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
Figure 2 for Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
Figure 3 for Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
Figure 4 for Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
* To appear at the International Conference On Intelligent Robots and Systems (IROS) 2018. Project webpage: http://vpg.cs.princeton.edu Summary video: https://youtu.be/-OkyX7ZlhiU 
  Access Paper or Ask Questions

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching


Apr 01, 2018
Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza, Daolin Ma, Orion Taylor, Melody Liu, Eudald Romo, Nima Fazeli, Ferran Alet, Nikhil Chavan Dafle, Rachel Holladay, Isabella Morona, Prem Qu Nair, Druck Green, Ian Taylor, Weber Liu, Thomas Funkhouser, Alberto Rodriguez

Figure 1 for Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Figure 2 for Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Figure 3 for Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Figure 4 for Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
* To appear at the International Conference on Robotics and Automation (ICRA) 2018. Project webpage: http://arc.cs.princeton.edu Summary video: https://youtu.be/6fG7zwGfIkI 
  Access Paper or Ask Questions

Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View


Dec 12, 2017
Shuran Song, Andy Zeng, Angel X. Chang, Manolis Savva, Silvio Savarese, Thomas Funkhouser

Figure 1 for Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
Figure 2 for Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
Figure 3 for Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
Figure 4 for Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
* Video summary: https://youtu.be/Au3GmktK-So 
  Access Paper or Ask Questions

Matterport3D: Learning from RGB-D Data in Indoor Environments


Sep 18, 2017
Angel Chang, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Nießner, Manolis Savva, Shuran Song, Andy Zeng, Yinda Zhang

Figure 1 for Matterport3D: Learning from RGB-D Data in Indoor Environments
Figure 2 for Matterport3D: Learning from RGB-D Data in Indoor Environments
Figure 3 for Matterport3D: Learning from RGB-D Data in Indoor Environments
Figure 4 for Matterport3D: Learning from RGB-D Data in Indoor Environments

  Access Paper or Ask Questions

Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks


Jul 02, 2017
Yinda Zhang, Shuran Song, Ersin Yumer, Manolis Savva, Joon-Young Lee, Hailin Jin, Thomas Funkhouser

Figure 1 for Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
Figure 2 for Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
Figure 3 for Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
Figure 4 for Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
* Updates camera ready version. Accepted by CVPR 2017 
  Access Paper or Ask Questions