Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

Object-Centric Learning with Slot Attention

Jun 26, 2020
Francesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran, Georg Heigold, Jakob Uszkoreit, Alexey Dosovitskiy, Thomas Kipf

  Access Model/Code and Paper
Learning Depth via Interaction

Mar 02, 2020
Antonio Loquercio, Alexey Dosovitskiy, Davide Scaramuzza

  Access Model/Code and Paper
The Visual Task Adaptation Benchmark

Oct 01, 2019
Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil Houlsby

  Access Model/Code and Paper
Deep Drone Racing: From Simulation to Reality with Domain Randomization

May 21, 2019
Antonio Loquercio, Elia Kaufmann, René Ranftl, Alexey Dosovitskiy, Vladlen Koltun, Davide Scaramuzza

* 12 pages. arXiv admin note: text overlap with arXiv:1806.08548 

  Access Model/Code and Paper
Benchmarking Classic and Learned Navigation in Complex 3D Environments

Mar 28, 2019
Dmytro Mishkin, Alexey Dosovitskiy, Vladlen Koltun

* Added CNN-Monodepth and OpenCV Stereo agents 

  Access Model/Code and Paper
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing

Mar 01, 2019
Elia Kaufmann, Mathias Gehrig, Philipp Foehn, René Ranftl, Alexey Dosovitskiy, Vladlen Koltun, Davide Scaramuzza

* IEEE International Conference on Robotics and Automation (ICRA), 2019 
* 6 pages (+1 references) 

  Access Model/Code and Paper
Frequency-Aware Model Predictive Control

Feb 08, 2019
Ruben Grandia, Farbod Farshidian, Alexey Dosovitskiy, René Ranftl, Marco Hutter

* IEEE Robotics and Automation Letters 2019 

  Access Model/Code and Paper
Learning agile and dynamic motor skills for legged robots

Jan 24, 2019
Jemin Hwangbo, Joonho Lee, Alexey Dosovitskiy, Dario Bellicoso, Vassilios Tsounis, Vladlen Koltun, Marco Hutter

* Science Robotics 4.26 (2019): eaau5872 

  Access Model/Code and Paper
Motion Perception in Reinforcement Learning with Dynamic Objects

Jan 10, 2019
Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox

  Access Model/Code and Paper
Driving Policy Transfer via Modularity and Abstraction

Dec 13, 2018
Matthias Müller, Alexey Dosovitskiy, Bernard Ghanem, Vladlen Koltun

* Accepted at Conference on Robotic Learning (CoRL'18) 

  Access Model/Code and Paper
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds

Oct 22, 2018
Eldar Insafutdinov, Alexey Dosovitskiy

  Access Model/Code and Paper
Deep Drone Racing: Learning Agile Flight in Dynamic Environments

Oct 09, 2018
Elia Kaufmann, Antonio Loquercio, Rene Ranftl, Alexey Dosovitskiy, Vladlen Koltun, Davide Scaramuzza

* Conference on Robotic Learning (CoRL), 2018 
* Accepted for publication in the Conference on Robotic Learning (CoRL) 2018, Zurich. 10 pages (+3 supplementary) 

  Access Model/Code and Paper
On Offline Evaluation of Vision-based Driving Models

Sep 13, 2018
Felipe Codevilla, Antonio M. López, Vladlen Koltun, Alexey Dosovitskiy

* Published at the ECCV 2018 conference 

  Access Model/Code and Paper
Artistic style transfer for videos and spherical images

Aug 05, 2018
Manuel Ruder, Alexey Dosovitskiy, Thomas Brox

* v3: added ref to conference. This paper is a successor of and overlaps with arXiv:1604.08610, International Journal of Computer Vision (IJCV), 2018 

  Access Model/Code and Paper
On Evaluation of Embodied Navigation Agents

Jul 18, 2018
Peter Anderson, Angel Chang, Devendra Singh Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, Amir R. Zamir

* Report of a working group on empirical methodology in navigation research. Authors are listed in alphabetical order 

  Access Model/Code and Paper
TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning

Jun 04, 2018
Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox

  Access Model/Code and Paper
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

Mar 22, 2018
Nikolaus Mayer, Eddy Ilg, Philipp Fischer, Caner Hazirbas, Daniel Cremers, Alexey Dosovitskiy, Thomas Brox

* added references (UCL dataset); added IJCV copyright information 

  Access Model/Code and Paper
End-to-end Driving via Conditional Imitation Learning

Mar 02, 2018
Felipe Codevilla, Matthias Müller, Antonio López, Vladlen Koltun, Alexey Dosovitskiy

* Published at the International Conference on Robotics and Automation (ICRA), 2018 

  Access Model/Code and Paper
Semi-parametric Topological Memory for Navigation

Mar 01, 2018
Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun

* Published at International Conference on Learning Representations (ICLR) 2018. Project website at 

  Access Model/Code and Paper
MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments

Dec 11, 2017
Manolis Savva, Angel X. Chang, Alexey Dosovitskiy, Thomas Funkhouser, Vladlen Koltun

* MINOS is a simulator designed to support research on end-to-end navigation 

  Access Model/Code and Paper
CARLA: An Open Urban Driving Simulator

Nov 10, 2017
Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun

* Published at the 1st Conference on Robot Learning (CoRL) 

  Access Model/Code and Paper
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

Aug 07, 2017
Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox

  Access Model/Code and Paper
Learning to Generate Chairs, Tables and Cars with Convolutional Networks

Aug 02, 2017
Alexey Dosovitskiy, Jost Tobias Springenberg, Maxim Tatarchenko, Thomas Brox

* v4: final PAMI version. New architecture figure 

  Access Model/Code and Paper
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

Apr 12, 2017
Anh Nguyen, Jeff Clune, Yoshua Bengio, Alexey Dosovitskiy, Jason Yosinski

* CVPR camera-ready 

  Access Model/Code and Paper
DeMoN: Depth and Motion Network for Learning Monocular Stereo

Apr 11, 2017
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox

* Camera ready version for CVPR 2017. Supplementary material included. Project page: 

  Access Model/Code and Paper
Learning to Act by Predicting the Future

Feb 14, 2017
Alexey Dosovitskiy, Vladlen Koltun

* Published as a conference paper at ICLR 2017 

  Access Model/Code and Paper
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Dec 06, 2016
Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, Thomas Brox

* Including supplementary material. For the video see: 

  Access Model/Code and Paper
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Nov 23, 2016
Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune

* 29 pages, 35 figures, NIPS camera-ready 

  Access Model/Code and Paper