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

GAN-Supervised Dense Visual Alignment


Dec 09, 2021
William Peebles, Jun-Yan Zhu, Richard Zhang, Antonio Torralba, Alexei Efros, Eli Shechtman

Figure 1 for GAN-Supervised Dense Visual Alignment
Figure 2 for GAN-Supervised Dense Visual Alignment
Figure 3 for GAN-Supervised Dense Visual Alignment
Figure 4 for GAN-Supervised Dense Visual Alignment
* Code available at https://www.github.com/wpeebles/gangealing . Project page and videos available at https://www.wpeebles.com/gangealing 
  Access Paper or Ask Questions

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning


Dec 09, 2021
Yining Hong, Li Yi, Joshua B. Tenenbaum, Antonio Torralba, Chuang Gan

Figure 1 for PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
Figure 2 for PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
Figure 3 for PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
Figure 4 for PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
* NeurIPS 2021. Project page: http://ptr.csail.mit.edu/ 
  Access Paper or Ask Questions

Editing a classifier by rewriting its prediction rules


Dec 02, 2021
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry

Figure 1 for Editing a classifier by rewriting its prediction rules
Figure 2 for Editing a classifier by rewriting its prediction rules
Figure 3 for Editing a classifier by rewriting its prediction rules
Figure 4 for Editing a classifier by rewriting its prediction rules

  Access Paper or Ask Questions

Learning to Compose Visual Relations


Nov 17, 2021
Nan Liu, Shuang Li, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba

Figure 1 for Learning to Compose Visual Relations
Figure 2 for Learning to Compose Visual Relations
Figure 3 for Learning to Compose Visual Relations
Figure 4 for Learning to Compose Visual Relations
* NeurIPS 2021 (Spotlight), first three authors contributed equally, Website: https://composevisualrelations.github.io/ 
  Access Paper or Ask Questions

EditGAN: High-Precision Semantic Image Editing


Nov 04, 2021
Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, Sanja Fidler

Figure 1 for EditGAN: High-Precision Semantic Image Editing
Figure 2 for EditGAN: High-Precision Semantic Image Editing
Figure 3 for EditGAN: High-Precision Semantic Image Editing
Figure 4 for EditGAN: High-Precision Semantic Image Editing

  Access Paper or Ask Questions

Ego4D: Around the World in 3,000 Hours of Egocentric Video


Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik

Figure 1 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 2 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 3 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 4 for Ego4D: Around the World in 3,000 Hours of Egocentric Video

  Access Paper or Ask Questions

OPEn: An Open-ended Physics Environment for Learning Without a Task


Oct 13, 2021
Chuang Gan, Abhishek Bhandwaldar, Antonio Torralba, Joshua B. Tenenbaum, Phillip Isola

Figure 1 for OPEn: An Open-ended Physics Environment for Learning Without a Task
Figure 2 for OPEn: An Open-ended Physics Environment for Learning Without a Task
Figure 3 for OPEn: An Open-ended Physics Environment for Learning Without a Task
Figure 4 for OPEn: An Open-ended Physics Environment for Learning Without a Task
* IROS 2021. Project page: http://open.csail.mit.edu/ 
  Access Paper or Ask Questions

Toward a Visual Concept Vocabulary for GAN Latent Space


Oct 08, 2021
Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba

Figure 1 for Toward a Visual Concept Vocabulary for GAN Latent Space
Figure 2 for Toward a Visual Concept Vocabulary for GAN Latent Space
Figure 3 for Toward a Visual Concept Vocabulary for GAN Latent Space
Figure 4 for Toward a Visual Concept Vocabulary for GAN Latent Space
* 15 pages, 13 figures. Accepted to ICCV 2021. Project page: https://visualvocab.csail.mit.edu 
  Access Paper or Ask Questions

Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions


Oct 07, 2021
Shuang Li, Yilun Du, Antonio Torralba, Josef Sivic, Bryan Russell

Figure 1 for Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
Figure 2 for Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
Figure 3 for Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
Figure 4 for Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions

  Access Paper or Ask Questions

Scaling up instance annotation via label propagation


Oct 05, 2021
Dim P. Papadopoulos, Ethan Weber, Antonio Torralba

Figure 1 for Scaling up instance annotation via label propagation
Figure 2 for Scaling up instance annotation via label propagation
Figure 3 for Scaling up instance annotation via label propagation
Figure 4 for Scaling up instance annotation via label propagation
* ICCV 2021 
  Access Paper or Ask Questions

Skill Induction and Planning with Latent Language


Oct 04, 2021
Pratyusha Sharma, Antonio Torralba, Jacob Andreas

Figure 1 for Skill Induction and Planning with Latent Language
Figure 2 for Skill Induction and Planning with Latent Language
Figure 3 for Skill Induction and Planning with Latent Language
Figure 4 for Skill Induction and Planning with Latent Language
* 13 pages, 6 figures 
  Access Paper or Ask Questions

Dynamic Modeling of Hand-Object Interactions via Tactile Sensing


Sep 09, 2021
Qiang Zhang, Yunzhu Li, Yiyue Luo, Wan Shou, Michael Foshey, Junchi Yan, Joshua B. Tenenbaum, Wojciech Matusik, Antonio Torralba

Figure 1 for Dynamic Modeling of Hand-Object Interactions via Tactile Sensing
Figure 2 for Dynamic Modeling of Hand-Object Interactions via Tactile Sensing
Figure 3 for Dynamic Modeling of Hand-Object Interactions via Tactile Sensing
Figure 4 for Dynamic Modeling of Hand-Object Interactions via Tactile Sensing
* IROS 2021. First two authors contributed equally. Project page: http://phystouch.csail.mit.edu/ 
  Access Paper or Ask Questions

What You Can Learn by Staring at a Blank Wall


Aug 30, 2021
Prafull Sharma, Miika Aittala, Yoav Y. Schechner, Antonio Torralba, Gregory W. Wornell, William T. Freeman, Fredo Durand

Figure 1 for What You Can Learn by Staring at a Blank Wall
Figure 2 for What You Can Learn by Staring at a Blank Wall
Figure 3 for What You Can Learn by Staring at a Blank Wall
Figure 4 for What You Can Learn by Staring at a Blank Wall

  Access Paper or Ask Questions

3D Neural Scene Representations for Visuomotor Control


Jul 08, 2021
Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba

Figure 1 for 3D Neural Scene Representations for Visuomotor Control
Figure 2 for 3D Neural Scene Representations for Visuomotor Control
Figure 3 for 3D Neural Scene Representations for Visuomotor Control
Figure 4 for 3D Neural Scene Representations for Visuomotor Control
* First two authors contributed equally. Project Page: https://3d-representation-learning.github.io/nerf-dy/ 
  Access Paper or Ask Questions

Learning to See by Looking at Noise


Jun 10, 2021
Manel Baradad, Jonas Wulff, Tongzhou Wang, Phillip Isola, Antonio Torralba

Figure 1 for Learning to See by Looking at Noise
Figure 2 for Learning to See by Looking at Noise
Figure 3 for Learning to See by Looking at Noise
Figure 4 for Learning to See by Looking at Noise

  Access Paper or Ask Questions

Measuring Generalization with Optimal Transport


Jun 07, 2021
Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba, Stefanie Jegelka

Figure 1 for Measuring Generalization with Optimal Transport
Figure 2 for Measuring Generalization with Optimal Transport
Figure 3 for Measuring Generalization with Optimal Transport
Figure 4 for Measuring Generalization with Optimal Transport

  Access Paper or Ask Questions

DriveGAN: Towards a Controllable High-Quality Neural Simulation


Apr 30, 2021
Seung Wook Kim, Jonah Philion, Antonio Torralba, Sanja Fidler

Figure 1 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 2 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 3 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 4 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
* CVPR 2021 Oral 
  Access Paper or Ask Questions

DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort


Apr 20, 2021
Yuxuan Zhang, Huan Ling, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler

Figure 1 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 2 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 3 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 4 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
* Accepted to CVPR 2021 as an Oral paper. Webpage: https://nv-tlabs.github.io/datasetGAN/ 
  Access Paper or Ask Questions

Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales


Apr 17, 2021
Jacob Andreas, GaΕ‘per BeguΕ‘, Michael M. Bronstein, Roee Diamant, Denley Delaney, Shane Gero, Shafi Goldwasser, David F. Gruber, Sarah de Haas, Peter Malkin, Roger Payne, Giovanni Petri, Daniela Rus, Pratyusha Sharma, Dan Tchernov, Pernille TΓΈnnesen, Antonio Torralba, Daniel Vogt, Robert J. Wood

Figure 1 for Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
Figure 2 for Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
Figure 3 for Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales
Figure 4 for Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales

  Access Paper or Ask Questions

BARF: Bundle-Adjusting Neural Radiance Fields


Apr 13, 2021
Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, Simon Lucey

Figure 1 for BARF: Bundle-Adjusting Neural Radiance Fields
Figure 2 for BARF: Bundle-Adjusting Neural Radiance Fields
Figure 3 for BARF: Bundle-Adjusting Neural Radiance Fields
Figure 4 for BARF: Bundle-Adjusting Neural Radiance Fields

  Access Paper or Ask Questions

Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization


Apr 12, 2021
Daiqing Li, Junlin Yang, Karsten Kreis, Antonio Torralba, Sanja Fidler

Figure 1 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 2 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 3 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 4 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
* CVPR2021 
  Access Paper or Ask Questions

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