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 Antonio Torralba

Antonio Torralba

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI


Mar 25, 2021
Chuang Gan, Siyuan Zhou, Jeremy Schwartz, Seth Alter, Abhishek Bhandwaldar, Dan Gutfreund, Daniel L. K. Yamins, James J DiCarlo, Josh McDermott, Antonio Torralba, Joshua B. Tenenbaum

Figure 1 for The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
Figure 2 for The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
Figure 3 for The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
Figure 4 for The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI
* Project page: http://tdw-transport.csail.mit.edu/ 
  Access Paper or Ask Questions

Paint by Word


Mar 24, 2021
David Bau, Alex Andonian, Audrey Cui, YeonHwan Park, Ali Jahanian, Aude Oliva, Antonio Torralba

Figure 1 for Paint by Word
Figure 2 for Paint by Word
Figure 3 for Paint by Word
Figure 4 for Paint by Word
* 10 pages, 9 figures 
  Access Paper or Ask Questions

Deep Feedback Inverse Problem Solver


Jan 19, 2021
Wei-Chiu Ma, Shenlong Wang, Jiayuan Gu, Sivabalan Manivasagam, Antonio Torralba, Raquel Urtasun

Figure 1 for Deep Feedback Inverse Problem Solver
Figure 2 for Deep Feedback Inverse Problem Solver
Figure 3 for Deep Feedback Inverse Problem Solver
Figure 4 for Deep Feedback Inverse Problem Solver
* ECCV 2020 Spotlight 
  Access Paper or Ask Questions

Energy-Based Models for Continual Learning


Nov 24, 2020
Shuang Li, Yilun Du, Gido M. van de Ven, Antonio Torralba, Igor Mordatch

Figure 1 for Energy-Based Models for Continual Learning
Figure 2 for Energy-Based Models for Continual Learning
Figure 3 for Energy-Based Models for Continual Learning
Figure 4 for Energy-Based Models for Continual Learning

  Access Paper or Ask Questions

Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration


Oct 19, 2020
Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Joshua B. Tenenbaum, Sanja Fidler, Antonio Torralba

Figure 1 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 2 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 3 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 4 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

  Access Paper or Ask Questions

Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering


Oct 18, 2020
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler

Figure 1 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 2 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 3 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 4 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

  Access Paper or Ask Questions

LID 2020: The Learning from Imperfect Data Challenge Results


Oct 17, 2020
Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, Liwei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc Van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He

Figure 1 for LID 2020: The Learning from Imperfect Data Challenge Results
Figure 2 for LID 2020: The Learning from Imperfect Data Challenge Results
Figure 3 for LID 2020: The Learning from Imperfect Data Challenge Results
Figure 4 for LID 2020: The Learning from Imperfect Data Challenge Results
* Summary of the 2nd Learning from Imperfect Data Workshop in conjunction with CVPR 2020 
  Access Paper or Ask Questions

Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space


Sep 14, 2020
Jonas Wulff, Antonio Torralba

Figure 1 for Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
Figure 2 for Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
Figure 3 for Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
Figure 4 for Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space

  Access Paper or Ask Questions

Understanding the Role of Individual Units in a Deep Neural Network


Sep 12, 2020
David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza, Bolei Zhou, Antonio Torralba

Figure 1 for Understanding the Role of Individual Units in a Deep Neural Network
Figure 2 for Understanding the Role of Individual Units in a Deep Neural Network
Figure 3 for Understanding the Role of Individual Units in a Deep Neural Network
Figure 4 for Understanding the Role of Individual Units in a Deep Neural Network
* Proceedings of the National Academy of Sciences 2020. Code at https://github.com/davidbau/dissect/ and website at https://dissect.csail.mit.edu/ 
  Access Paper or Ask Questions

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement


Aug 24, 2020
William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba

Figure 1 for The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
Figure 2 for The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
Figure 3 for The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
Figure 4 for The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
* ECCV 2020 (Spotlight). Code available at https://github.com/wpeebles/hessian_penalty . Project page and videos available at https://www.wpeebles.com/hessian-penalty 
  Access Paper or Ask Questions

Detecting natural disasters, damage, and incidents in the wild


Aug 20, 2020
Ethan Weber, Nuria Marzo, Dim P. Papadopoulos, Aritro Biswas, Agata Lapedriza, Ferda Ofli, Muhammad Imran, Antonio Torralba

Figure 1 for Detecting natural disasters, damage, and incidents in the wild
Figure 2 for Detecting natural disasters, damage, and incidents in the wild
Figure 3 for Detecting natural disasters, damage, and incidents in the wild
Figure 4 for Detecting natural disasters, damage, and incidents in the wild
* ECCV 2020 
  Access Paper or Ask Questions

Rewriting a Deep Generative Model


Jul 30, 2020
David Bau, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba

Figure 1 for Rewriting a Deep Generative Model
Figure 2 for Rewriting a Deep Generative Model
Figure 3 for Rewriting a Deep Generative Model
Figure 4 for Rewriting a Deep Generative Model
* ECCV 2020 (oral). Code at https://github.com/davidbau/rewriting. For videos and demos see https://rewriting.csail.mit.edu/ 
  Access Paper or Ask Questions

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events


Jul 27, 2020
Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba, Joshua B. Tenenbaum

Figure 1 for Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
Figure 2 for Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
Figure 3 for Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
Figure 4 for Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
* Project page: http://noisy-agent.csail.mit.edu 
  Access Paper or Ask Questions

Foley Music: Learning to Generate Music from Videos


Jul 21, 2020
Chuang Gan, Deng Huang, Peihao Chen, Joshua B. Tenenbaum, Antonio Torralba

Figure 1 for Foley Music: Learning to Generate Music from Videos
Figure 2 for Foley Music: Learning to Generate Music from Videos
Figure 3 for Foley Music: Learning to Generate Music from Videos
Figure 4 for Foley Music: Learning to Generate Music from Videos
* ECCV 2020. Project page: http://foley-music.csail.mit.edu 
  Access Paper or Ask Questions

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations


Jul 06, 2020
Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka

Figure 1 for Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Figure 2 for Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Figure 3 for Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Figure 4 for Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
* International Conference on Machine Learning, 2020 
 * arXiv admin note: text overlap with arXiv:1910.05804 
  Access Paper or Ask Questions

Debiased Contrastive Learning


Jul 05, 2020
Ching-Yao Chuang, Joshua Robinson, Lin Yen-Chen, Antonio Torralba, Stefanie Jegelka

Figure 1 for Debiased Contrastive Learning
Figure 2 for Debiased Contrastive Learning
Figure 3 for Debiased Contrastive Learning
Figure 4 for Debiased Contrastive Learning

  Access Paper or Ask Questions

Causal Discovery in Physical Systems from Videos


Jul 02, 2020
Yunzhu Li, Antonio Torralba, Animashree Anandkumar, Dieter Fox, Animesh Garg

Figure 1 for Causal Discovery in Physical Systems from Videos
Figure 2 for Causal Discovery in Physical Systems from Videos
Figure 3 for Causal Discovery in Physical Systems from Videos
Figure 4 for Causal Discovery in Physical Systems from Videos
* Project page: https://yunzhuli.github.io/V-CDN/ 
  Access Paper or Ask Questions

Diverse Image Generation via Self-Conditioned GANs


Jun 18, 2020
Steven Liu, Tongzhou Wang, David Bau, Jun-Yan Zhu, Antonio Torralba

Figure 1 for Diverse Image Generation via Self-Conditioned GANs
Figure 2 for Diverse Image Generation via Self-Conditioned GANs
Figure 3 for Diverse Image Generation via Self-Conditioned GANs
Figure 4 for Diverse Image Generation via Self-Conditioned GANs
* CVPR 2020. Code: https://github.com/stevliu/self-conditioned-gan. Webpage: http://selfcondgan.csail.mit.edu/ 
  Access Paper or Ask Questions

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos


Jun 16, 2020
Andrew Rouditchenko, Angie Boggust, David Harwath, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Rogerio Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James Glass

Figure 1 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 2 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 3 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 4 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

  Access Paper or Ask Questions

Learning to Simulate Dynamic Environments with GameGAN


May 25, 2020
Seung Wook Kim, Yuhao Zhou, Jonah Philion, Antonio Torralba, Sanja Fidler

Figure 1 for Learning to Simulate Dynamic Environments with GameGAN
Figure 2 for Learning to Simulate Dynamic Environments with GameGAN
Figure 3 for Learning to Simulate Dynamic Environments with GameGAN
Figure 4 for Learning to Simulate Dynamic Environments with GameGAN
* CVPR 2020 
  Access Paper or Ask Questions

Semantic Photo Manipulation with a Generative Image Prior


May 15, 2020
David Bau, Hendrik Strobelt, William Peebles, Jonas, Bolei Zhou, Jun-Yan Zhu, Antonio Torralba

Figure 1 for Semantic Photo Manipulation with a Generative Image Prior
Figure 2 for Semantic Photo Manipulation with a Generative Image Prior
Figure 3 for Semantic Photo Manipulation with a Generative Image Prior
Figure 4 for Semantic Photo Manipulation with a Generative Image Prior
* Bau, David, et al. "Semantic photo manipulation with a generative image prior." ACM Transactions on Graphics (TOG) 38.4 (2019) 
 * SIGGRAPH 2019 
  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

Music Gesture for Visual Sound Separation


Apr 20, 2020
Chuang Gan, Deng Huang, Hang Zhao, Joshua B. Tenenbaum, Antonio Torralba

Figure 1 for Music Gesture for Visual Sound Separation
Figure 2 for Music Gesture for Visual Sound Separation
Figure 3 for Music Gesture for Visual Sound Separation
Figure 4 for Music Gesture for Visual Sound Separation
* CVPR 2020. Project page: http://music-gesture.csail.mit.edu 
  Access Paper or Ask Questions

Self-supervised Moving Vehicle Tracking with Stereo Sound


Oct 25, 2019
Chuang Gan, Hang Zhao, Peihao Chen, David Cox, Antonio Torralba

Figure 1 for Self-supervised Moving Vehicle Tracking with Stereo Sound
Figure 2 for Self-supervised Moving Vehicle Tracking with Stereo Sound
Figure 3 for Self-supervised Moving Vehicle Tracking with Stereo Sound
Figure 4 for Self-supervised Moving Vehicle Tracking with Stereo Sound
* To appear at ICCV 2019. Project page: http://sound-track.csail.mit.edu 
  Access Paper or Ask Questions

Seeing What a GAN Cannot Generate


Oct 24, 2019
David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba

Figure 1 for Seeing What a GAN Cannot Generate
Figure 2 for Seeing What a GAN Cannot Generate
Figure 3 for Seeing What a GAN Cannot Generate
Figure 4 for Seeing What a GAN Cannot Generate
* ICCV 2019 oral; http://ganseeing.csail.mit.edu/ 
  Access Paper or Ask Questions

Gaze360: Physically Unconstrained Gaze Estimation in the Wild


Oct 22, 2019
Petr Kellnhofer, Adria Recasens, Simon Stent, Wojciech Matusik, Antonio Torralba

Figure 1 for Gaze360: Physically Unconstrained Gaze Estimation in the Wild
Figure 2 for Gaze360: Physically Unconstrained Gaze Estimation in the Wild
Figure 3 for Gaze360: Physically Unconstrained Gaze Estimation in the Wild
Figure 4 for Gaze360: Physically Unconstrained Gaze Estimation in the Wild
* International Conference in Computer Vision, 2019 
  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

The Role of Embedding Complexity in Domain-invariant Representations


Oct 13, 2019
Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka

Figure 1 for The Role of Embedding Complexity in Domain-invariant Representations
Figure 2 for The Role of Embedding Complexity in Domain-invariant Representations

  Access Paper or Ask Questions

Neural Turtle Graphics for Modeling City Road Layouts


Oct 04, 2019
Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler

Figure 1 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 2 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 3 for Neural Turtle Graphics for Modeling City Road Layouts
Figure 4 for Neural Turtle Graphics for Modeling City Road Layouts
* ICCV-2019 Oral 
  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