Towards Total Recall in Industrial Anomaly DetectionKarsten Roth , Latha Pemula , Joaquin Zepeda , Bernhard Schölkopf , Thomas Brox , and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2022 |
I am a researcher at Amazon in Tübingen. Before, I was W3 professor at the University of Würzburg, group leader at the Bernstein Center of Computational Neuroscience at the University of Tübingen and affiliated with the Max Planck Institute for Intelligent Systems in Tübingen as a senior research scientist.
I want to enable computers to understand the physical world around us. I am mostly interested in models that infer semantic and physical properties of visual data.
We have several openings for internship on a number of topics, year round. Please drop me an email if you are interested.
Towards Total Recall in Industrial Anomaly DetectionKarsten Roth , Latha Pemula , Joaquin Zepeda , Bernhard Schölkopf , Thomas Brox , and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2022 |
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory PredictionOsama Makansi , Julius von Kuegelen , Francesco Locatello , Peter Gehler , Dominik Janzing , Thomas Brox , and Bernhard Schölkopf International Conference on Learning Representations (ICLR), 2022 |
The Role of Pretrained Representations for the OOD Generalization of RL AgentsAndrea Dittadi , Frederik Traeuble , Manuel Wüthrich , Felix Widmaier , Peter Gehler , Ole Winther , Francesco Locatello , Olivier Bachem , Bernhard Schölkopf , and Stefan Bauer International Conference on Learning Representations (ICLR), 2022 |
Visual Representation Learning Does Not Generalize Strongly Within the Same DomainLukas Schott , Julius von Kuegelen , Frederik Traeuble , Peter Gehler , Chris Russell , Matthias Bethge , Bernhard Schölkopf , Francesco Locatello , and Wieland Brendl International Conference on Learning Representations (ICLR), 2022 |
Dynamic Inference with Neural InterpretersMuhammad Waleed Gondal , Nasim Rahaman , Shruti Joshi , Peter Gehler , Yoshua Bengio , Francesco Locatello , and Bernhard Schölkopf Neural Information and Processing Systems (NeurIPS), 2021 |
Backward-Compatible Prediction Updates: A Probabilistic ApproachFrederik Traeuble , Julius von Kuegelen , Matthäus Kleindessner , Francesco Locatello , Bernhard Schölkopf , and Peter Gehler Neural Information and Processing Systems (NeurIPS), 2021 |
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video RepresentationsMohammadreza Zolfaghari , Yi Zhu , Peter Gehler , and Thomas Brox International Conference on Computer Vision (ICCV), 2021 |
Adapting ImageNet-scale models to complex distribution shifts with self-learningEvgenia Rusak , Steffen Schneider , Peter Gehler , Oliver Bringmann , Wieland Brendl , and Matthias Bethge ICLR workshop on Weakly Supervised Learning (ICLR-w), 2021 |
Towards causal generative scene models via competition of expertsJulius von Kuegelen , Ivan Ustyuzhaninov , Peter Gehler , Matthias Bethge , and Bernhard Schölkopf ICLR workshop on Causal Learning for Decision Making (ICLR-w), 2020 |
Learning Task-Specific Generalized Convolutions in the Permutohedral LatticeAnne Wannenwetsch , Martin Kiefel , Peter Gehler , and Stefan Roth German Conference on Pattern Recognition (GCPR), 2019 |
Learning an event sequence embedding for dense event-based deep stereoStepan Tulyakov , Francois Fleuret , Martin Kiefel , Peter Gehler , and Michael Hirsch International Conference on Computer Vision (ICCV), 2019 |
Providing a single Ground-truth for Illuminant Estimation for the ColorChecker DatasetGhalia Hemrit , Graham Finlayson , Arjan Gijsenij , Peter Gehler , Simone Bianco , Mark Drew , Brian Funt , and Lilong Shi Pattern Analysis and Machine Intelligence (PAMI), 2019 |
Deep Directional Statistics: Pose Estimation with Uncertainty QuantificationSergey Prokudin , Peter Gehler , and Sebastian Nowozin European Conference on Computer Vision (ECCV), 2018 |
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape EstimationMohamed Omran , Christoph Lassner , Gerard Pons-Moll , Peter Gehler , and Bernt Schiele International Conference on 3DVision (3DV), 2018 |
A Generative Model of People in ClothingChristoph Lassner , Gerard Pons-Moll , and Peter Gehler International Conference on Computer Vision (ICCV), 2017 |
Semantic Video CNNs through Representation WarpingRaghudeep Gadde , Varun Jampani , and Peter Gehler International Conference on Computer Vision (ICCV), 2017 |
Towards Accurate Marker-less Human Shape and Pose Estimation over TimeYinghao Huang , Federica Bogo , Christoph Lassner , Angjoo Kanazawa , Peter Gehler , Javier Romero , Ijaz Akther , and Michael Black International Conference on 3D Vision (3DV), 2017 |
Learning To Filter Object DetectionsSergey Prokudin , Daniel Kappler , Sebastian Nowozin , and Peter Gehler German Conference on Patter Recognition (GCPR), 2017 |
A Curious Problem with Using the Colour Checker Dataset for Illuminant EstimationGhalia Hemrit , Graham Finlayson , Peter Gehler , and Arjan Gijsenij Color and Imaging Conference (CIC), 2017 |
Reflectance Adaptive Filtering Improves Intrinsic Image EstimationThomas Nestmeyer and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2017 |
Video Propagation NetworksVarun Jampani , Raghudeep Gadde , and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2017 |
Unite the People: Closing the Loop Between 3D and 2D Human RepresentationsChristoph Lassner , Javier Romero , Martin Kiefel , Federica Bogo , Michael Black , and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2017 |
Efficient 2D and 3D Facade Segmentation using Auto-ContextRaghudeep Gadde , Varun Jampani , Renaud Marlet , and Peter Gehler Pattern Analysis and Machine Intelligence (PAMI), 2017 |
barrista -- caffe well servedChristoph Lassner , Martin Kiefel , Daniel Kappler , and Peter Gehler Multimedia 2016 Open Source Software Competition (ACMMM), 2016 |
Superpixel Convolutional Networks using Bilateral InceptionsRaghudeep Gadde , Varun Jampani , Martin Kiefel , Daniel Kappler , and Peter Gehler Proceedings of the European Conference on Computer Vision (ECCV), 2016 |
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single ImageFederica Bogo , Angjoo Kanazawa , Christoph Lassner , Peter Gehler , Javier Romero , and Michael Black Proceedings of the European Conference on Computer Vision (ECCV), 2016 |
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose EstimationLeonid Pishchulin , Eldar Insafutdinov , Siyu Tang , Björn Andres , Mykhaylo Andriluka , Peter Gehler , and Bernt Schiele Computer Vision and Pattern Recognition (CVPR), 2016 |
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural NetworksVarun Jampani , Martin Kiefel , and Peter Gehler Computer Vision and Pattern Recognition (CVPR), 2016 |
| Proceedings of the 37th German Conference on Pattern RecognitionJürgen Gall , Peter Gehler , and Bastian Leibe GCPR Proceedings, 2015 |
3D Object Class Detection in the WildBojan Pepik , Michael Stark , Peter Gehler , Tobias Ritschel , and Bernt Schiele CVPR workshop on 3D from a Single Image (CVPR-W), 2015 |
Permutohedral Lattice CNNsMartin Kiefel , Varun Jampani , and Peter Gehler International Confernence on Learning Representations Workshops, 2015 |
| The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision ModelsVarun Jampani , Sebastian Nowozin , Matt Loper , and Peter Gehler Computer Vision and Image Understanding (CVIU), 2015 |
| Multi-view and 3D Deformable Part ModelsBojan Pepik , Michael Stark , Peter Gehler , and Bernt Schiele Pattern Analysis and Machine Intelligence (PAMI), 2015 |
Efficient Facade Segmentation using Auto-ContextVarun Jampani , Raghudeep Gadde , and Peter Gehler Winter Conference on Applications of Computer Vision (WACV), 2015 |
| Advanced Structured PredictionSebastian Nowozin , Peter Gehler , Jeremy Jancsary , and Christoph Lampert MIT press, 2014 |
Intrinsic VideoNaejin Kong , Peter Gehler , and Michael Black Proceedings of the European Conference on Computer Vision (ECCV), 2014 |
Human Pose Estimation with Fields of PartsMartin Kiefel and Peter Gehler Proceedings of the European Conference on Computer Vision (ECCV), 2014 |
Efficient Non-linear Markov Models for Human MotionAndreas Lehrmann , Peter Gehler , and Sebastian Nowozin Computer Vision and Pattern Recognition (CVPR), 2014 |
Human Pose Estimation: New Benchmark and State of the Art AnalysisMykhaylo Andriluka , Leonid Pishchulin , Peter Gehler , and Bernt Schiele Computer Vision and Pattern Recognition (CVPR), 2014 |
Multi-View Priors for Learning Detectors from Sparse Viewpoint DataBojan Pepik , Michael Stark , Peter Gehler , and Bernt Schiele International Conference on Learning Representations (ICLR), 2014 |
Strong Appearance and Expressive Spatial Models for Human Pose EstimationLeonid Pishchulin , Mykhaylo Andriluka , Peter Gehler , and Bernt Schiele International Conference on Computer Vision (ICCV), 2013 |
A Non-parametric Bayesian Network Prior of Human PoseAndreas Lehrmann , Peter Gehler , and Sebastian Nowozin International Conference on Computer Vision (ICCV), 2013 |
Branch&Rank for Efficient Object DetectionAlain Lehmann , Peter Gehler , and Luc Van Gool International Journal of Computer Vision (IJCV), 2013 |
Poselet conditioned pictorial structuresLeonid Pishchulin , Mykhaylo Andriluka , Peter Gehler , and Bernt Schiele IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013 |
Occlusion Patterns for Object Class DetectionBojan Pepik , Michael Stark , Peter Gehler , and Bernt Schiele IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013 |
3D2PM - 3D Deformable Part ModelsBojan Pepik , Peter Gehler , Michael Stark , and Bernt Schiele Proceedings of the European Conference on Computer Vision (ECCV), 2012 |
Pottics - The Potts Topic Model for Semantic Image SegmentationChristoph Dann , Peter Gehler , Stefan Roth , and Sebastian Nowozin Proceedings of 34th DAGM Symposium (DAGM), 2012 |
Teaching 3D Geometry to Deformable Part ModelsBojan Pepik , Michael Stark , Peter Gehler , and Bernt Schiele IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 |
Learning Search Based Inference for Object DetectionPeter Gehler and Alain Lehmann ICML workshop on Inferning, 2012 |
Recovering Intrinsic Images with a Global Sparsity Prior on ReflectancePeter Gehler , Carsten Rother , Martin Kiefel , Lumin Zhang , and Bernhard Schölkopf Advances in Neural Information Processing Systems (NIPS), 2011 |
Branch&Rank - Non-Linear Object DetectionAlain Lehmann , Peter Gehler , and Luc Van Gool Proceedings of the British Machine Vision Conference (BMVC), 2011 |
Learning Output Kernels with Block Coordinate DescentFrancesco Dinuzzo , Cheng Soon Ong , Peter Gehler , and Gianluigi Pillonetto International Conference on Machine Learning (ICML), 2011 |
Scene Carving - Scene Consistent Image RetargetingAlex Mansfield , Peter Gehler , Luc Van Gool , and Carsten Rother European Conference on Computer Vision (ECCV), 2010 |
Visibility Maps for Improving Seam CarvingAlex Mansfield , Peter Gehler , Luc Van Gool , and Carsten Rother Media Retargeting Workshop (ECCV), 2010 pdf bib supplementary poster slides project page code scholar |
On Parameter Learning in CRF-based Approaches to Object Class Image SegmentationSebastian Nowozin , Peter Gehler , and Christoph Lampert European Conference on Computer Vision (ECCV), 2010 |
An introduction to Kernel Learning AlgorithmsPeter Gehler and Bernhard Schölkopf In Kernel Methods for Remote Sensing Data Analysis, 2009 |
Let the kernel figure it out; Principled learning of pre-processing for kernel classifiersPeter Gehler and Sebastian Nowozin Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2009 |
On feature combination for multiclass object classificationPeter Gehler and Sebastian Nowozin International Conference on Computer Vision (ICCV), 2009 |
Infinite Kernel LearningPeter Gehler and Sebastian Nowozin Kernel Learning - Automatic Selection of Optimal Kernels (NIPS workshop on Kernel Learning), 2008 |
Infinite Kernel LearningPeter Gehler and Sebastian Nowozin Technical Report 178, Max Planck Institute, 2008 |
Bayesian Color Constancy RevisitedPeter Gehler , Carsten Rother , Andrew Blake , Tom Minka , and Toby Sharp IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2008 |
Deterministic Annealing for Multiple-Instance LearningPeter Gehler and Olivier Chapelle Artificial Intelligence and Statistics (AIStats), 2007 |
Implicit Wiener Series, Part II Regularised estimationPeter Gehler and Matthias O. Franz Technical Report 148, Max Planck Institute, 2006 |
The rate adapting poisson model for information retrieval and object recognitionPeter Gehler , Alex Holub , and Max Welling Proceedings of the 23rd international conference on Machine learning (ICML), 2006 |
Products of ``Edge-perts''Peter Gehler and Max Welling Advances in Neural Information Processing Systems 18 (NIPS), 2006 |
How to choose the covariance for Gaussian process regression independently of the basisMatthias O. Franz and Peter Gehler Proceedings of the Workshop Gaussian Processes in Practice, 2006 |
Member of ELLIS.