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 Alexey Dosovitskiy

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations


Nov 29, 2021
Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi

* Project website: https://srt-paper.github.io/ 

  Access Paper or Ask Questions

Conditional Object-Centric Learning from Video


Nov 24, 2021
Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour, Georg Heigold, Rico Jonschkowski, Alexey Dosovitskiy, Klaus Greff

* Project page at https://slot-attention-video.github.io/ 

  Access Paper or Ask Questions

Do Vision Transformers See Like Convolutional Neural Networks?


Aug 19, 2021
Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, Alexey Dosovitskiy


  Access Paper or Ask Questions

MLP-Mixer: An all-MLP Architecture for Vision


May 17, 2021
Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, Alexey Dosovitskiy

* Fixed parameter counts in Table 1 

  Access Paper or Ask Questions

Differentiable Patch Selection for Image Recognition


Apr 07, 2021
Jean-Baptiste Cordonnier, Aravindh Mahendran, Alexey Dosovitskiy, Dirk Weissenborn, Jakob Uszkoreit, Thomas Unterthiner

* Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021. Code available at https://github.com/google-research/google-research/tree/master/ptopk_patch_selection/ 

  Access Paper or Ask Questions

Learning Object-Centric Video Models by Contrasting Sets


Nov 20, 2020
Sindy Löwe, Klaus Greff, Rico Jonschkowski, Alexey Dosovitskiy, Thomas Kipf

* NeurIPS 2020 Workshop on Object Representations for Learning and Reasoning 

  Access Paper or Ask Questions

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale


Oct 22, 2020
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

* Fine-tuning code and pre-trained models are available at https://github.com/google-research/vision_transformer 

  Access Paper or Ask Questions

NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections


Aug 13, 2020
Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, Daniel Duckworth

* Project website: https://nerf-w.github.io. Ricardo Martin-Brualla, Noha Radwan, and Mehdi S. M. Sajjadi contributed equally to this work. Updated affiliations 

  Access Paper or Ask Questions

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 Paper or Ask Questions

Learning Depth via Interaction


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


  Access Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

Motion Perception in Reinforcement Learning with Dynamic Objects


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


  Access Paper or Ask Questions

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) http://proceedings.mlr.press/v87/mueller18a.html 

  Access Paper or Ask Questions

Unsupervised Learning of Shape and Pose with Differentiable Point Clouds


Oct 22, 2018
Eldar Insafutdinov, Alexey Dosovitskiy


  Access Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions