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 Eddy Ilg

Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors


May 09, 2021
Deeksha Dangwal, Vincent T. Lee, Hyo Jin Kim, Tianwei Shen, Meghan Cowan, Rajvi Shah, Caroline Trippel, Brandon Reagen, Timothy Sherwood, Vasileios Balntas, Armin Alaghi, Eddy Ilg

* 13 pages 

  Access Paper or Ask Questions

Domain Adaptation of Learned Features for Visual Localization


Aug 21, 2020
Sungyong Baik, Hyo Jin Kim, Tianwei Shen, Eddy Ilg, Kyoung Mu Lee, Chris Sweeney

* BMVC 2020 

  Access Paper or Ask Questions

TLIO: Tight Learned Inertial Odometry


Jul 10, 2020
Wenxin Liu, David Caruso, Eddy Ilg, Jing Dong, Anastasios I. Mourikis, Kostas Daniilidis, Vijay Kumar, Jakob Engel

* Correcting graph and bibliography. Adding journal reference information and DOI, in IEEE Robotics and Automation Letters 

  Access Paper or Ask Questions

Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction


Apr 11, 2020
Rohan Chabra, Jan Eric Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, Richard Newcombe


  Access Paper or Ask Questions

Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction


Jun 09, 2019
Osama Makansi, Eddy Ilg, Özgün Cicek, Thomas Brox

* In CVPR 2019 

  Access Paper or Ask Questions

FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images


Aug 20, 2018
Osama Makansi, Eddy Ilg, Thomas Brox

* See video at: https://www.youtube.com/watch?v=HdMeb20Rybs 

  Access Paper or Ask Questions

Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation


Aug 08, 2018
Eddy Ilg, Tonmoy Saikia, Margret Keuper, Thomas Brox

* Accepted to ECCV 2018 as poster. See video at: https://www.youtube.com/watch?v=SwOdSaBRysI 

  Access Paper or Ask Questions

Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow


Aug 06, 2018
Eddy Ilg, Özgün Çiçek, Silvio Galesso, Aaron Klein, Osama Makansi, Frank Hutter, Thomas Brox

* Accepted to ECCV 2018 as poster. See Video at: https://youtu.be/HvyovWSo8uE 

  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

Lucid Data Dreaming for Multiple Object Tracking


Dec 14, 2017
Anna Khoreva, Rodrigo Benenson, Eddy Ilg, Thomas Brox, Bernt Schiele


  Access Paper or Ask Questions

End-to-End Learning of Video Super-Resolution with Motion Compensation


Jul 03, 2017
Osama Makansi, Eddy Ilg, Thomas Brox

* Accepted to GCPR2017 

  Access Paper or Ask Questions

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: http://lmb.informatik.uni-freiburg.de/people/ummenhof/depthmotionnet/ 

  Access Paper or Ask Questions

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: http://lmb.informatik.uni-freiburg.de/Publications/2016/IMKDB16/ 

  Access Paper or Ask Questions

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


Dec 07, 2015
Nikolaus Mayer, Eddy Ilg, Philip Häusser, Philipp Fischer, Daniel Cremers, Alexey Dosovitskiy, Thomas Brox

* Includes supplementary material 

  Access Paper or Ask Questions

FlowNet: Learning Optical Flow with Convolutional Networks


May 04, 2015
Philipp Fischer, Alexey Dosovitskiy, Eddy Ilg, Philip Häusser, Caner Hazırbaş, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, Thomas Brox

* Added supplementary material 

  Access Paper or Ask Questions