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 Björn Ommer

Geometry-Free View Synthesis: Transformers and no 3D Priors


Apr 15, 2021
Robin Rombach, Patrick Esser, Björn Ommer

* Code available at https://git.io/JOnwn 

  Access Paper or Ask Questions

Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes


Mar 31, 2021
Dmytro Kotovenko, Matthias Wright, Arthur Heimbrecht, Björn Ommer

* Accepted at CVPR2021 

  Access Paper or Ask Questions

Behavior-Driven Synthesis of Human Dynamics


Mar 08, 2021
Andreas Blattmann, Timo Milbich, Michael Dorkenwald, Björn Ommer

* Accepted to CVPR 2021 as Poster 

  Access Paper or Ask Questions

Taming Transformers for High-Resolution Image Synthesis


Dec 17, 2020
Patrick Esser, Robin Rombach, Björn Ommer


  Access Paper or Ask Questions

A Note on Data Biases in Generative Models


Dec 04, 2020
Patrick Esser, Robin Rombach, Björn Ommer

* Extended Abstract for the NeurIPS 2020 Workshop on Machine Learning for Creativity and Design 

  Access Paper or Ask Questions

S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning


Oct 01, 2020
Karsten Roth, Timo Milbich, Björn Ommer, Joseph Paul Cohen, Marzyeh Ghassemi


  Access Paper or Ask Questions

Unsupervised Part Discovery by Unsupervised Disentanglement


Sep 10, 2020
Sandro Braun, Patrick Esser, Björn Ommer

* GCPR 2020 (Oral) 

  Access Paper or Ask Questions

Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs


Aug 04, 2020
Robin Rombach, Patrick Esser, Björn Ommer

* ECCV 2020. Project page and code at https://compvis.github.io/invariances/ 

  Access Paper or Ask Questions

Network Fusion for Content Creation with Conditional INNs


May 27, 2020
Robin Rombach, Patrick Esser, Björn Ommer

* AI for Content Creation at CVPR2020 

  Access Paper or Ask Questions

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning


Apr 29, 2020
Timo Milbich, Karsten Roth, Homanga Bharadhwaj, Samarth Sinha, Yoshua Bengio, Björn Ommer, Joseph Paul Cohen

* 18 pages 

  Access Paper or Ask Questions

A Disentangling Invertible Interpretation Network for Explaining Latent Representations


Apr 27, 2020
Patrick Esser, Robin Rombach, Björn Ommer

* CVPR 2020. Project Page at https://compvis.github.io/iin/ 

  Access Paper or Ask Questions

Sharing Matters for Generalization in Deep Metric Learning


Apr 12, 2020
Timo Milbich, Karsten Roth, Biagio Brattoli, Björn Ommer

* Technical Report 

  Access Paper or Ask Questions

PADS: Policy-Adapted Sampling for Visual Similarity Learning


Mar 28, 2020
Karsten Roth, Timo Milbich, Björn Ommer

* Accepted to CVPR2020 

  Access Paper or Ask Questions

Learning to Correct Overexposed and Underexposed Photos


Mar 25, 2020
Mahmoud Afifi, Konstantinos G. Derpanis, Björn Ommer, Michael S. Brown


  Access Paper or Ask Questions

A Content Transformation Block For Image Style Transfer


Mar 18, 2020
Dmytro Kotovenko, Artsiom Sanakoyeu, Pingchuan Ma, Sabine Lang, Björn Ommer

* Accepted to CVPR 2019 

  Access Paper or Ask Questions

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning


Mar 12, 2020
Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen


  Access Paper or Ask Questions

Unsupervised Representation Learning by Discovering Reliable Image Relations


Nov 18, 2019
Timo Milbich, Omair Ghori, Ferran Diego, Björn Ommer

* Accepted for Publication in 'Pattern Recognition Journal' 

  Access Paper or Ask Questions

Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis


Oct 22, 2019
Patrick Esser, Johannes Haux, Björn Ommer

* ICCV 2019. Project page at https://compvis.github.io/robust-disentangling/ 

  Access Paper or Ask Questions

MIC: Mining Interclass Characteristics for Improved Metric Learning


Sep 25, 2019
Karsten Roth, Biagio Brattoli, Björn Ommer

* 8 pages, 10 figures, accepted to ICCV 2019 

  Access Paper or Ask Questions

Multi-Scale Convolutions for Learning Context Aware Feature Representations


Jun 17, 2019
Nikolai Ufer, Kam To Lui, Katja Schwarz, Paul Warkentin, Björn Ommer


  Access Paper or Ask Questions

Divide and Conquer the Embedding Space for Metric Learning


Jun 14, 2019
Artsiom Sanakoyeu, Vadim Tschernezki, Uta Büchler, Björn Ommer

* The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 471-480 
* Source code: https://github.com/CompVis/metric-learning-divide-and-conquer 

  Access Paper or Ask Questions

Unsupervised Part-Based Disentangling of Object Shape and Appearance


Mar 16, 2019
Dominik Lorenz, Leonard Bereska, Timo Milbich, Björn Ommer

* CVPR 2019 Oral 

  Access Paper or Ask Questions

Cross and Learn: Cross-Modal Self-Supervision


Nov 09, 2018
Nawid Sayed, Biagio Brattoli, Björn Ommer

* GCPR 2018 

  Access Paper or Ask Questions

Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning


Jul 30, 2018
Uta Büchler, Biagio Brattoli, Björn Ommer

* Accepted for publication at ECCV 2018 

  Access Paper or Ask Questions

A Style-Aware Content Loss for Real-time HD Style Transfer


Jul 28, 2018
Artsiom Sanakoyeu, Dmytro Kotovenko, Sabine Lang, Björn Ommer

* Accepted at ECCV18 (Oral) 

  Access Paper or Ask Questions

A Variational U-Net for Conditional Appearance and Shape Generation


Apr 12, 2018
Patrick Esser, Ekaterina Sutter, Björn Ommer

* CVPR 2018 (Spotlight). Project Page at https://compvis.github.io/vunet/ 

  Access Paper or Ask Questions