Publications

    Antonio Torralba

  • Michael Chang, Tomer Ullman, Antonio Torralba, Joshua B. Tenenbaum:
    A Compositional Object-Based Approach To Learning Physical Dynamics (web) (bibtex)
    Proceedings of the 5th International Conference on Learning Representations
    #intuitive physics, #simulation, #deep learning, #unsupervised learning, #scene understanding
    @article{MichaelChang:2017:07f51,
    author = {Michael Chang and Tomer Ullman and Antonio Torralba and Joshua B. Tenenbaum},
    journal = {Proceedings of the 5th International Conference on Learning Representations},
    title = {A Compositional Object-Based Approach To Learning Physical Dynamics},
    year = {2017},
    keywords = {intuitive physics, simulation, deep learning, unsupervised learning, scene understanding},
    doi = {},
    url = {https://arxiv.org/abs/1612.00341}
    }
  • Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman:
    Single Image 3D Interpreter Network (web) (bibtex)
    European Conference in Computer Vision (ECCV)
    #deep learning, #self-supervised learning, #3d vision
    @article{JiajunWu:2016:770f7,
    author = {Jiajun Wu and Tianfan Xue and Joseph J. Lim and Yuandong Tian and Joshua B. Tenenbaum and Antonio Torralba and William T. Freeman},
    journal = {European Conference in Computer Vision (ECCV)},
    title = {Single Image 3D Interpreter Network},
    year = {2016},
    keywords = {deep learning, self-supervised learning, 3d vision},
    doi = {},
    url = {http://3dinterpreter.csail.mit.edu/}
    }
  • Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman:
    3D Interpreter Networks for Viewer-Centered Wireframe Modeling (web) (bibtex)
    International Journal of Computer Vision (IJCV)
    #3d vision, #deep learning
    @article{JiajunWu:2018:ad749,
    author = {Jiajun Wu and Tianfan Xue and Joseph J. Lim and Yuandong Tian and Joshua B. Tenenbaum and Antonio Torralba and William T. Freeman},
    journal = {International Journal of Computer Vision (IJCV)},
    title = {3D Interpreter Networks for Viewer-Centered Wireframe Modeling},
    year = {2018},
    keywords = {3d vision, deep learning},
    doi = {},
    url = {http://3dinterpreter.csail.mit.edu/}
    }
  • Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, Antonio Torralba:
    Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, Fluids (web) (bibtex)
    International Conference on Learning Representations (ICLR), 2019
    #dynamics predicting, #planning and control
    @article{YunzhuLi:2019:4a458,
    author = {Yunzhu Li and Jiajun Wu and Russ Tedrake and Joshua B. Tenenbaum and Antonio Torralba},
    journal = {International Conference on Learning Representations (ICLR), 2019},
    title = {Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, Fluids},
    year = {2019},
    keywords = {dynamics predicting, planning and control},
    doi = {},
    url = {http://dpi.csail.mit.edu/}
    }
  • Shunyu Yao, Tzu-Ming Harry Hsu, Jun-Yan Zhu, Jiajun Wu, Antonio Torralba, William T. Freeman, Joshua B. Tenenbaum:
    3D-Aware Scene Manipulation via Inverse Graphics (web) (bibtex)
    Advances in Neural Information Processing Systems (NeurIPS)
    #3d vision, #deep learning, #scene understanding
    @article{ShunyuYao:2018:a9aef,
    author = {Shunyu Yao and Tzu-Ming Harry Hsu and Jun-Yan Zhu and Jiajun Wu and Antonio Torralba and William T. Freeman and Joshua B. Tenenbaum},
    journal = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {3D-Aware Scene Manipulation via Inverse Graphics},
    year = {2018},
    keywords = {3d vision, deep learning, scene understanding},
    doi = {},
    url = {http://3dsdn.csail.mit.edu/}
    }
  • Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, Joshua B. Tenenbaum:
    Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (web) (bibtex)
    Advances in Neural Information Processing Systems (NeurIPS)
    #visual reasoning, #deep learning, #scene understanding
    @article{KexinYi:2018:18b7f,
    author = {Kexin Yi and Jiajun Wu and Chuang Gan and Antonio Torralba and Pushmeet Kohli and Joshua B. Tenenbaum},
    journal = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding},
    year = {2018},
    keywords = {visual reasoning, deep learning, scene understanding},
    doi = {},
    url = {http://nsvqa.csail.mit.edu/}
    }
  • Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Joshua B. Tenenbaum, William T. Freeman:
    Visual Object Networks: Image Generation with Disentangled 3D Representations (web) (bibtex)
    Advances in Neural Information Processing Systems (NeurIPS)
    #3d vision, #deep learning
    @article{Jun-YanZhu:2018:3aa73,
    author = {Jun-Yan Zhu and Zhoutong Zhang and Chengkai Zhang and Jiajun Wu and Antonio Torralba and Joshua B. Tenenbaum and William T. Freeman},
    journal = {Advances in Neural Information Processing Systems (NeurIPS)},
    title = {Visual Object Networks: Image Generation with Disentangled 3D Representations},
    year = {2018},
    keywords = {3d vision, deep learning},
    doi = {},
    url = {http://von.csail.mit.edu/}
    }

add/edit publications