Alexey Dosovitskiy

research

∙ 11/25/2021

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

A classical problem in computer vision is to infer a 3D scene representa...

0 Mehdi S. M. Sajjadi, et al. ∙

research

∙ 08/19/2021

Do Vision Transformers See Like Convolutional Neural Networks?

Convolutional neural networks (CNNs) have so far been the de-facto model...

33 Jojo Yun, et al. ∙

research

∙ 05/04/2021

MLP-Mixer: An all-MLP Architecture for Vision

Convolutional Neural Networks (CNNs) are the go-to model for computer vi...

18 Ilya Tolstikhin, et al. ∙

research

∙ 04/07/2021

Differentiable Patch Selection for Image Recognition

Neural Networks require large amounts of memory and compute to process h...

75 Jean-Baptiste Cordonnier, et al. ∙

research

∙ 10/22/2020

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

While the Transformer architecture has become the de-facto standard for ...

6 Alexey Dosovitskiy, et al. ∙

research

∙ 08/05/2020

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

We present a learning-based method for synthesizing novel views of compl...

0 Ricardo Martin-Brualla, et al. ∙

research

∙ 03/02/2020

Learning Depth via Interaction

Motivated by the astonishing capabilities of natural intelligent agents ...

8 Antonio Loquercio, et al. ∙

research

∙ 05/21/2019

Deep Drone Racing: From Simulation to Reality with Domain Randomization

Dynamically changing environments, unreliable state estimation, and oper...

0 Antonio Loquercio, et al. ∙

research

∙ 01/30/2019

Benchmarking Classic and Learned Navigation in Complex 3D Environments

Navigation research is attracting renewed interest with the advent of le...

12 Dmytro Mishkin, et al. ∙

research

∙ 01/24/2019

Learning agile and dynamic motor skills for legged robots

Legged robots pose one of the greatest challenges in robotics. Dynamic a...

2 Jemin Hwangbo, et al. ∙

research

∙ 01/10/2019

Motion Perception in Reinforcement Learning with Dynamic Objects

In dynamic environments, learned controllers are supposed to take motion...

0 Artemij Amiranashvili, et al. ∙

research

∙ 10/22/2018

Unsupervised Learning of Shape and Pose with Differentiable Point Clouds

We address the problem of learning accurate 3D shape and camera pose fro...

0 Eldar Insafutdinov, et al. ∙

research

∙ 10/15/2018

Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing

Autonomous micro aerial vehicles still struggle with fast and agile mane...

0 Elia Kaufmann, et al. ∙

research

∙ 09/13/2018

On Offline Evaluation of Vision-based Driving Models

Autonomous driving models should ideally be evaluated by deploying them ...

0 Felipe Codevilla, et al. ∙

research

∙ 09/12/2018

Frequency-Aware Model Predictive Control

Transferring solutions found by trajectory optimization to robotic hardw...

0 Ruben Grandia, et al. ∙

research

∙ 07/18/2018

On Evaluation of Embodied Navigation Agents

Skillful mobile operation in three-dimensional environments is a primary...

0 Peter Anderson, et al. ∙

research

∙ 06/22/2018

Deep Drone Racing: Learning Agile Flight in Dynamic Environments

Autonomous agile flight brings up fundamental challenges in robotics, su...

0 Elia Kaufmann, et al. ∙

research

∙ 06/04/2018

TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning

Our understanding of reinforcement learning (RL) has been shaped by theo...

0 Artemij Amiranashvili, et al. ∙

research

∙ 04/25/2018

Driving Policy Transfer via Modularity and Abstraction

End-to-end approaches to autonomous driving have high sample complexity ...

0 Matthias Müller, et al. ∙

research

∙ 03/01/2018

Semi-parametric Topological Memory for Navigation

We introduce a new memory architecture for navigation in previously unse...

0 Nikolay Savinov, et al. ∙

research

∙ 01/19/2018

What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

The finding that very large networks can be trained efficiently and reli...

0 Nikolaus Mayer, et al. ∙

research

∙ 12/11/2017

MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments

We present MINOS, a simulator designed to support the development of mul...

0 Manolis Savva, et al. ∙

research

∙ 11/10/2017

CARLA: An Open Urban Driving Simulator

We introduce CARLA, an open-source simulator for autonomous driving rese...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 10/06/2017

End-to-end Driving via Conditional Imitation Learning

Deep networks trained on demonstrations of human driving have learned to...

0 Felipe Codevilla, et al. ∙

research

∙ 08/13/2017

Artistic style transfer for videos and spherical images

Manually re-drawing an image in a certain artistic style takes a profess...

0 Manuel Ruder, et al. ∙

research

∙ 03/28/2017

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

We present a deep convolutional decoder architecture that can generate v...

0 Maxim Tatarchenko, et al. ∙

research

∙ 12/07/2016

DeMoN: Depth and Motion Network for Learning Monocular Stereo

In this paper we formulate structure from motion as a learning problem. ...

0 Benjamin Ummenhofer, et al. ∙

research

∙ 12/06/2016

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

The FlowNet demonstrated that optical flow estimation can be cast as a l...

0 Eddy Ilg, et al. ∙

research

∙ 11/30/2016

Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

Generating high-resolution, photo-realistic images has been a long-stand...

0 Anh Nguyen, et al. ∙

research

∙ 11/06/2016

Learning to Act by Predicting the Future

We present an approach to sensorimotor control in immersive environments...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 05/30/2016

Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Deep neural networks (DNNs) have demonstrated state-of-the-art results o...

0 Anh Nguyen, et al. ∙

research

∙ 02/08/2016

Generating Images with Perceptual Similarity Metrics based on Deep Networks

Image-generating machine learning models are typically trained with loss...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 12/07/2015

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Recent work has shown that optical flow estimation can be formulated as ...

0 Nikolaus Mayer, et al. ∙

research

∙ 06/09/2015

Inverting Visual Representations with Convolutional Networks

Feature representations, both hand-designed and learned ones, are often ...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 04/26/2015

FlowNet: Learning Optical Flow with Convolutional Networks

Convolutional neural networks (CNNs) have recently been very successful ...

0 Philipp Fischer, et al. ∙

research

∙ 12/21/2014

Striving for Simplicity: The All Convolutional Net

Most modern convolutional neural networks (CNNs) used for object recogni...

0 Jost Tobias Springenberg, et al. ∙

research

∙ 11/21/2014

Learning to Generate Chairs, Tables and Cars with Convolutional Networks

We train generative 'up-convolutional' neural networks which are able to...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 06/26/2014

Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Deep convolutional networks have proven to be very successful in learnin...

0 Alexey Dosovitskiy, et al. ∙

research

∙ 05/22/2014

Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT

Latest results indicate that features learned via convolutional neural n...

0 Philipp Fischer, et al. ∙

research

∙ 12/18/2013

Unsupervised feature learning by augmenting single images

When deep learning is applied to visual object recognition, data augment...

0 Alexey Dosovitskiy, et al. ∙

Alexey Dosovitskiy

Featured Co-authors