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 Jiajun Wu

Jiajun Wu

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning


Mar 30, 2021
Zhenfang Chen, Jiayuan Mao, Jiajun Wu, Kwan-Yee Kenneth Wong, Joshua B. Tenenbaum, Chuang Gan

Figure 1 for Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Figure 2 for Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Figure 3 for Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Figure 4 for Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
* ICLR 2021. Project page: http://dcl.csail.mit.edu/ 
  Access Paper or Ask Questions

Repopulating Street Scenes


Mar 30, 2021
Yifan Wang, Andrew Liu, Richard Tucker, Jiajun Wu, Brian L. Curless, Steven M. Seitz, Noah Snavely

Figure 1 for Repopulating Street Scenes
Figure 2 for Repopulating Street Scenes
Figure 3 for Repopulating Street Scenes
Figure 4 for Repopulating Street Scenes
* CVPR 2021 
  Access Paper or Ask Questions

Learning Temporal Dynamics from Cycles in Narrated Video


Jan 07, 2021
Dave Epstein, Jiajun Wu, Cordelia Schmid, Chen Sun

Figure 1 for Learning Temporal Dynamics from Cycles in Narrated Video
Figure 2 for Learning Temporal Dynamics from Cycles in Narrated Video
Figure 3 for Learning Temporal Dynamics from Cycles in Narrated Video
Figure 4 for Learning Temporal Dynamics from Cycles in Narrated Video

  Access Paper or Ask Questions

Language-Mediated, Object-Centric Representation Learning


Dec 31, 2020
Ruocheng Wang, Jiayuan Mao, Samuel J. Gershman, Jiajun Wu

* First two authors contributed equally; last two authors contributed equally. Project page: https://lang-orl.github.io/ 
  Access Paper or Ask Questions

Augmenting Policy Learning with Routines Discovered from a Demonstration


Dec 24, 2020
Zelin Zhao, Chuang Gan, Jiajun Wu, Xiaoxiao Guo, Joshua B. Tenenbaum

Figure 1 for Augmenting Policy Learning with Routines Discovered from a Demonstration
Figure 2 for Augmenting Policy Learning with Routines Discovered from a Demonstration
Figure 3 for Augmenting Policy Learning with Routines Discovered from a Demonstration
Figure 4 for Augmenting Policy Learning with Routines Discovered from a Demonstration
* To appear in AAAI-21. Code is available at https://github.com/sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL- 
  Access Paper or Ask Questions

Object-Centric Diagnosis of Visual Reasoning


Dec 21, 2020
Jianwei Yang, Jiayuan Mao, Jiajun Wu, Devi Parikh, David D. Cox, Joshua B. Tenenbaum, Chuang Gan

Figure 1 for Object-Centric Diagnosis of Visual Reasoning
Figure 2 for Object-Centric Diagnosis of Visual Reasoning
Figure 3 for Object-Centric Diagnosis of Visual Reasoning
Figure 4 for Object-Centric Diagnosis of Visual Reasoning

  Access Paper or Ask Questions

Neural Radiance Flow for 4D View Synthesis and Video Processing


Dec 17, 2020
Yilun Du, Yinan Zhang, Hong-Xing Yu, Joshua B. Tenenbaum, Jiajun Wu

Figure 1 for Neural Radiance Flow for 4D View Synthesis and Video Processing
Figure 2 for Neural Radiance Flow for 4D View Synthesis and Video Processing
Figure 3 for Neural Radiance Flow for 4D View Synthesis and Video Processing
Figure 4 for Neural Radiance Flow for 4D View Synthesis and Video Processing
* Website: https://yilundu.github.io/nerflow/ 
  Access Paper or Ask Questions

Object-Centric Neural Scene Rendering


Dec 15, 2020
Michelle Guo, Alireza Fathi, Jiajun Wu, Thomas Funkhouser

Figure 1 for Object-Centric Neural Scene Rendering
Figure 2 for Object-Centric Neural Scene Rendering
Figure 3 for Object-Centric Neural Scene Rendering
Figure 4 for Object-Centric Neural Scene Rendering
* Summary Video: https://youtu.be/NtR7xgxSL1U Project Webpage: https://shellguo.com/osf 
  Access Paper or Ask Questions

pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis


Dec 02, 2020
Eric R. Chan, Marco Monteiro, Petr Kellnhofer, Jiajun Wu, Gordon Wetzstein

Figure 1 for pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
Figure 2 for pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
Figure 3 for pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
Figure 4 for pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

  Access Paper or Ask Questions

Multi-Plane Program Induction with 3D Box Priors


Nov 22, 2020
Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Noah Snavely, Jiajun Wu

Figure 1 for Multi-Plane Program Induction with 3D Box Priors
Figure 2 for Multi-Plane Program Induction with 3D Box Priors
Figure 3 for Multi-Plane Program Induction with 3D Box Priors
Figure 4 for Multi-Plane Program Induction with 3D Box Priors
* NeurIPS 2020. First two authors contributed equally. Project page: http://bpi.csail.mit.edu 
  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

Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection


Sep 24, 2020
Yue Wang, Alireza Fathi, Jiajun Wu, Thomas Funkhouser, Justin Solomon

Figure 1 for Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
Figure 2 for Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
Figure 3 for Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
Figure 4 for Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
* The Workshop on Perception for Autonomous Driving at ECCV2020 
  Access Paper or Ask Questions

Unsupervised Discovery of 3D Physical Objects from Video


Jul 24, 2020
Yilun Du, Kevin Smith, Tomer Ulman, Joshua Tenenbaum, Jiajun Wu

Figure 1 for Unsupervised Discovery of 3D Physical Objects from Video
Figure 2 for Unsupervised Discovery of 3D Physical Objects from Video
Figure 3 for Unsupervised Discovery of 3D Physical Objects from Video
Figure 4 for Unsupervised Discovery of 3D Physical Objects from Video

  Access Paper or Ask Questions

End-to-End Optimization of Scene Layout


Jul 23, 2020
Andrew Luo, Zhoutong Zhang, Jiajun Wu, Joshua B. Tenenbaum

Figure 1 for End-to-End Optimization of Scene Layout
Figure 2 for End-to-End Optimization of Scene Layout
Figure 3 for End-to-End Optimization of Scene Layout
Figure 4 for End-to-End Optimization of Scene Layout
* CVPR 2020 (Oral). Project page: http://3dsln.csail.mit.edu/ 
  Access Paper or Ask Questions

Perspective Plane Program Induction from a Single Image


Jun 25, 2020
Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

Figure 1 for Perspective Plane Program Induction from a Single Image
Figure 2 for Perspective Plane Program Induction from a Single Image
Figure 3 for Perspective Plane Program Induction from a Single Image
Figure 4 for Perspective Plane Program Induction from a Single Image
* CVPR 2020. First two authors contributed equally. Project page: http://p3i.csail.mit.edu/ 
  Access Paper or Ask Questions

Learning Physical Graph Representations from Visual Scenes


Jun 24, 2020
Daniel M. Bear, Chaofei Fan, Damian Mrowca, Yunzhu Li, Seth Alter, Aran Nayebi, Jeremy Schwartz, Li Fei-Fei, Jiajun Wu, Joshua B. Tenenbaum, Daniel L. K. Yamins

Figure 1 for Learning Physical Graph Representations from Visual Scenes
Figure 2 for Learning Physical Graph Representations from Visual Scenes
Figure 3 for Learning Physical Graph Representations from Visual Scenes
Figure 4 for Learning Physical Graph Representations from Visual Scenes
* 23 pages; corrected affiliations and acknowledgments 
  Access Paper or Ask Questions

When is Particle Filtering Efficient for POMDP Sequential Planning?


Jun 10, 2020
Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu

Figure 1 for When is Particle Filtering Efficient for POMDP Sequential Planning?

  Access Paper or Ask Questions

Data Representation for Deep Learning with Prior Knowledge of Symmetric Wireless Tasks


May 27, 2020
Chengjian Sun, Jiajun Wu, Chenyang Yang

Figure 1 for Data Representation for Deep Learning with Prior Knowledge of Symmetric Wireless Tasks
Figure 2 for Data Representation for Deep Learning with Prior Knowledge of Symmetric Wireless Tasks
Figure 3 for Data Representation for Deep Learning with Prior Knowledge of Symmetric Wireless Tasks
Figure 4 for Data Representation for Deep Learning with Prior Knowledge of Symmetric Wireless Tasks
* 7 pages, 5 figures, submitted to IEEE for possible publication 
  Access Paper or Ask Questions

Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks


May 18, 2020
Chengjian Sun, Jiajun Wu, Chenyang Yang

Figure 1 for Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks
Figure 2 for Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks
Figure 3 for Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks
Figure 4 for Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks
* 7 pages, 5 figures, submitted to IEEE for possible publication 
  Access Paper or Ask Questions

Visual Grounding of Learned Physical Models


Apr 28, 2020
Yunzhu Li, Toru Lin, Kexin Yi, Daniel Bear, Daniel L. K. Yamins, Jiajun Wu, Joshua B. Tenenbaum, Antonio Torralba

Figure 1 for Visual Grounding of Learned Physical Models
Figure 2 for Visual Grounding of Learned Physical Models
Figure 3 for Visual Grounding of Learned Physical Models
Figure 4 for Visual Grounding of Learned Physical Models
* The second and the third authors contributed equally to this paper, and are listed in alphabetical order. Project Page: http://visual-physics-grounding.csail.mit.edu/ 
  Access Paper or Ask Questions

Visual Concept-Metaconcept Learning


Feb 04, 2020
Chi Han, Jiayuan Mao, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu

Figure 1 for Visual Concept-Metaconcept Learning
Figure 2 for Visual Concept-Metaconcept Learning
Figure 3 for Visual Concept-Metaconcept Learning
Figure 4 for Visual Concept-Metaconcept Learning
* NeurIPS 2019. First two authors contributed equally. Project page: http://vcml.csail.mit.edu/ 
  Access Paper or Ask Questions

Look, Listen, and Act: Towards Audio-Visual Embodied Navigation


Dec 25, 2019
Chuang Gan, Yiwei Zhang, Jiajun Wu, Boqing Gong, Joshua B. Tenenbaum

Figure 1 for Look, Listen, and Act: Towards Audio-Visual Embodied Navigation
Figure 2 for Look, Listen, and Act: Towards Audio-Visual Embodied Navigation
Figure 3 for Look, Listen, and Act: Towards Audio-Visual Embodied Navigation
Figure 4 for Look, Listen, and Act: Towards Audio-Visual Embodied Navigation

  Access Paper or Ask Questions

Entity Abstraction in Visual Model-Based Reinforcement Learning


Dec 04, 2019
Rishi Veerapaneni, John D. Co-Reyes, Michael Chang, Michael Janner, Chelsea Finn, Jiajun Wu, Joshua B. Tenenbaum, Sergey Levine

Figure 1 for Entity Abstraction in Visual Model-Based Reinforcement Learning
Figure 2 for Entity Abstraction in Visual Model-Based Reinforcement Learning
Figure 3 for Entity Abstraction in Visual Model-Based Reinforcement Learning
Figure 4 for Entity Abstraction in Visual Model-Based Reinforcement Learning
* Accepted at CoRL 2019 
  Access Paper or Ask Questions

Accurate Vision-based Manipulation through Contact Reasoning


Nov 08, 2019
Alina Kloss, Maria Bauza, Jiajun Wu, Joshua B. Tenenbaum, Alberto Rodriguez, Jeannette Bohg

Figure 1 for Accurate Vision-based Manipulation through Contact Reasoning
Figure 2 for Accurate Vision-based Manipulation through Contact Reasoning
Figure 3 for Accurate Vision-based Manipulation through Contact Reasoning
Figure 4 for Accurate Vision-based Manipulation through Contact Reasoning
* submitted to ICRA 2020 
  Access Paper or Ask Questions

Proactive Optimization with Unsupervised Learning


Oct 29, 2019
Jiajun Wu, Chengjian Sun, Chenyang Yang

Figure 1 for Proactive Optimization with Unsupervised Learning
Figure 2 for Proactive Optimization with Unsupervised Learning
Figure 3 for Proactive Optimization with Unsupervised Learning
Figure 4 for Proactive Optimization with Unsupervised Learning
* 6 pages, 3 figures, submitted to IEEE for possible publication 
  Access Paper or Ask Questions

Learning Compositional Koopman Operators for Model-Based Control


Oct 18, 2019
Yunzhu Li, Hao He, Jiajun Wu, Dina Katabi, Antonio Torralba

Figure 1 for Learning Compositional Koopman Operators for Model-Based Control
Figure 2 for Learning Compositional Koopman Operators for Model-Based Control
Figure 3 for Learning Compositional Koopman Operators for Model-Based Control
Figure 4 for Learning Compositional Koopman Operators for Model-Based Control
* The first two authors contributed equally to this paper. Project Page: http://koopman.csail.mit.edu/ Video: https://www.youtube.com/watch?v=idFH4K16cfQ&feature=youtu.be 
  Access Paper or Ask Questions

CLEVRER: CoLlision Events for Video REpresentation and Reasoning


Oct 03, 2019
Kexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, Joshua B. Tenenbaum

Figure 1 for CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Figure 2 for CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Figure 3 for CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Figure 4 for CLEVRER: CoLlision Events for Video REpresentation and Reasoning
* The first two authors contributed equally to this work. Project page: http://clevrer.csail.mit.edu/ 
  Access Paper or Ask Questions

Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs


Sep 28, 2019
Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum

Figure 1 for Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs
Figure 2 for Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs
Figure 3 for Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs
Figure 4 for Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs

  Access Paper or Ask Questions