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

Denoised MDPs: Learning World Models Better Than the World Itself


Jul 18, 2022
Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian

Figure 1 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 2 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 3 for Denoised MDPs: Learning World Models Better Than the World Itself
Figure 4 for Denoised MDPs: Learning World Models Better Than the World Itself
* Project page: https://ssnl.github.io/denoised_mdp/ Code: https://github.com/facebookresearch/denoised_mdp 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Finding Fallen Objects Via Asynchronous Audio-Visual Integration


Jul 07, 2022
Chuang Gan, Yi Gu, Siyuan Zhou, Jeremy Schwartz, Seth Alter, James Traer, Dan Gutfreund, Joshua B. Tenenbaum, Josh McDermott, Antonio Torralba

Figure 1 for Finding Fallen Objects Via Asynchronous Audio-Visual Integration
Figure 2 for Finding Fallen Objects Via Asynchronous Audio-Visual Integration
Figure 3 for Finding Fallen Objects Via Asynchronous Audio-Visual Integration
Figure 4 for Finding Fallen Objects Via Asynchronous Audio-Visual Integration
* CVPR 2022. Project page: http://fallen-object.csail.mit.edu 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Local Relighting of Real Scenes


Jul 06, 2022
Audrey Cui, Ali Jahanian, Agata Lapedriza, Antonio Torralba, Shahin Mahdizadehaghdam, Rohit Kumar, David Bau

Figure 1 for Local Relighting of Real Scenes
Figure 2 for Local Relighting of Real Scenes
Figure 3 for Local Relighting of Real Scenes
Figure 4 for Local Relighting of Real Scenes
* 15 pages, 15 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Virtual Correspondence: Humans as a Cue for Extreme-View Geometry


Jun 16, 2022
Wei-Chiu Ma, Anqi Joyce Yang, Shenlong Wang, Raquel Urtasun, Antonio Torralba

Figure 1 for Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
Figure 2 for Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
Figure 3 for Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
Figure 4 for Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
* CVPR 2022. Project page: https://people.csail.mit.edu/weichium/virtual-correspondence/ 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Disentangling visual and written concepts in CLIP


Jun 15, 2022
Joanna Materzynska, Antonio Torralba, David Bau

Figure 1 for Disentangling visual and written concepts in CLIP
Figure 2 for Disentangling visual and written concepts in CLIP
Figure 3 for Disentangling visual and written concepts in CLIP
Figure 4 for Disentangling visual and written concepts in CLIP

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Compositional Visual Generation with Composable Diffusion Models


Jun 08, 2022
Nan Liu, Shuang Li, Yilun Du, Antonio Torralba, Joshua B. Tenenbaum

Figure 1 for Compositional Visual Generation with Composable Diffusion Models
Figure 2 for Compositional Visual Generation with Composable Diffusion Models
Figure 3 for Compositional Visual Generation with Composable Diffusion Models
Figure 4 for Compositional Visual Generation with Composable Diffusion Models
* Project website: https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/ First three authors contributed equally 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps


Jun 06, 2022
Seung Wook Kim, Karsten Kreis, Daiqing Li, Antonio Torralba, Sanja Fidler

Figure 1 for Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps
Figure 2 for Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps
Figure 3 for Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps
Figure 4 for Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps
* CVPR 2022 Oral 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction


May 05, 2022
Yining Hong, Kaichun Mo, Li Yi, Leonidas J. Guibas, Antonio Torralba, Joshua B. Tenenbaum, Chuang Gan

Figure 1 for Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
Figure 2 for Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
Figure 3 for Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
Figure 4 for Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
* CVPR 2022. Project page: http://fixing-malfunctional.csail.mit.edu 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>