Publications
For my google scholar profile, please click here.
Preprints
Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller, DARTS for Inverse Problems: a Study on Hyperparameter Sensitivity (Preprint)
Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein, What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors (Preprint)
Christina Runkel, Christian Etmann, Michael Moeller, Carola-Bibiane Schönlieb, Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization (Preprint)
2023
Hannah Dröge, Zorah Lähner, Yuval Bahat, Onofre Martorell Nadal, Felix Heide, Michael Moeller, Kissing to Find a Match: Efficient Low-Rank Permutation Representation, Accepted at NeurIPS 2023.
Jan Philipp Schneider, Mishal Fatima, Jovita Lukasik, Andreas Kolb, Margret Keuper, Michael Moeller, Implicit Representations for Image Segmentation, accepted at the NeurIPS workshop on Unifying Representations in Neural Models 2023.
Zorah Lähner, Michael Moeller, On the Direct Alignment of Latent Spaces, accepted at the NeurIPS workshop on Unifying Representations in Neural Models 2023.
Andreas Görlitz, Michael Moeller, Andreas Kolb, Coherent Enhancement of Depth Images and Normal Maps using Second-order Geometric Models on Weighted Finite Graphs, accepted at 3DV 2023.
Samira Kabri, Alexander Auras, Danilo Riccio, Hartmut Bauermeister, Martin Benning, Michael Moeller, Martin Burger, Convergent Data-driven Regularizations for CT Reconstruction, Accepted in Communications on Applied Mathematics and Computation. (Preprint)
Maolin Gao, Paul Roetzer, Marvin Eisenberger, Zorah Laehner, Michael Moeller, Daniel Cremers and Florian Bernard, SIGMA: Scale-Invariant Global Sparse Shape Matching, ICCV 2023.
Jovita Lukasik, Michael Moeller and Margret Keuper, An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness, GCPR 2023. (Preprint)
Jovita Lukasik, Jonas Geiping, Michael Moeller and Margret Keuper, Differentiable Architecture Search: a One-Shot Method? Accepted at the AutoML Conference 2023 Workshops.
John Meshreki, Jan Philipp Schneider, Onofre Martorell, Michael Moeller, Ivo Ihrke, Modelling Vignetting in Fourier Ptychographic Microscopy, International Symposium on Computational Sensing 2023.
Kanchana Vaishnavi Gandikota, Paramanand Chandramouli, Hannah Dröge, Michael Moeller, Evaluating Adversarial Robustness of Low dose CT Recovery, MIDL 2023. (Paper)
Harshil Bhatia, Edith Tretschk, Zorah Lähner, Marcel Seelbach Benkner, Michael Moeller, Christian Theobalt, Vladislav Golyanik, CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes, CVPR 2023. (Paper)
Christina Runkel, Michael Moeller, Carola-Bibiane Schönlieb, Christian Etmann, Learning Posterior Distributions in Underdetermined Inverse Problems , SSVM 2023. (Paper)
Marcel Seelbach Benkner, Maximilian Krahn, Edith Tretschk, Zorah Lähner, Michael Moeller, Vladislav Golyanik, Learning QUBO Forms in Quantum Annealing, ICLR 2023. (Paper)
Aya Souliman, Matthias Kahl, Daniel Stock, Michael Moeller, Bernd Engel and Peter Haring Bolívar, Defect Detection in Bi-directional Glass Fabric Reinforced Thermoplastics Based on 3D THz Imaging. IEEE Trans. on Terrehertz Science and Technology, 2023. (Paper)
2022
Hannah Dröge, Yuval Bahat, Felix Heide, Michael Moeller, Explorable Data Consistent CT Reconstruction, accepted at BMVC 2022
Kanchana Vaishnavi Gandikota, Jonas Geiping, Zorah Lähner, Adam Czapliński, Michael Moeller, A simple strategy to make neural networks provably invariant, accepted at ACCV 2022 (old Preprint)
Zekarias Negese, Hartmut Bauermeister, Michael Moeller, Emanuele Rodolà and Zorah Lähner, Light-Weight Learning-Based Depth Estimation From A Single Image, accepted at the ATHENA Research Book vol 1, to be published with the University of Maribor Press, 2022.
Marius Bock, Alexander Hölzemann, Michael Moeller, Kristof Van Laerhoven, Investigating (Re)current state-of-the-art in Human Activity Recognition Datasets, accepted in Frontiers in Computer Science, section Mobile and Ubiquitous Computing.
Lukas Koestler, Daniel Grittner, Michael Moeller, Daniel Cremers, Zorah Lähner, Intrinsic Neural Fields: Learning Functions on Manifolds, accepted at ECCV 2022 (Preprint).
Kanchana Vaishnavi Gandikota, Paramanand Chandramouli, Michael Moeller, On adversarial robustness of image deblurring, accepted at ICIP 2022.
Andreas Goerlitz, Michael Moeller, Andreas Kolb, FL0C: Fast L0 cut pursuit for estimation of piecewise constant functions, accepted at ICIP 2022.
Hannah Dröge, Thomas Möllenhoff, Michael Moeller, Non-smooth energy dissipating networks, accepted at ICIP 2022.
Hartmut Bauermeister, Emanuel Laude, Thomas Möllenhoff, Michael Möller, Daniel Cremers, Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields, accepted at the SIAM Journal on Imaging Sciences (Preprint)
Jonas Geiping, Micah Goldblum, Phil Pope, Michael Moeller, Tom Goldstein, Stochastic Training is Not Necessary for Generalization, ICLR 2022. (Paper)
Tak Ming Wong, Hartmut Bauermeister, Matthias Kahl, Peter Haring Bolivar, Michael Moeller, Andreas Kolb, Deep Optimization Prior for THz Model Parameter Estimation, WACV 2022.
2021
Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller, DARTS for Inverse Problems: a Study on Stability, NeurIPS Workshop on "Deep Learning for Inverse Problems" 2021.
Hannah Dröge, Baichuan Yuan, Rafael Llerena, Jesse Yen, Michael Moeller, Andrea L. Bertozzi, Mitral Valve Segmentation using Robust Nonnegative Matrix Factorization, MDPI Special Issue "Inverse Problems and Imaging" 2021.
Marcel Seelbach Benkner, Zorah Lähner, Vladislav Golyanik, Christof Wunderlich, Christian Theobalt, Michael Moeller, Q-Match: Iterative Shape Matching via Quantum Annealing, Accepted at ICCV 2021. (Preprint)
Marius Bock, Alexander Hölzemann, Michael Moeller, Kristof Van Laerhoven, Improving Deep Learning for HAR with shallow LSTMs, Best Paper Award at ISWC 2021. (Preprint)
Hannah Dröge, Michael Möller, Learning or Modelling? An Analysis of Single Image Segmentation based on Scribble Information, ICIP 2021. (Paper)
Rama Krishna Kandukuri, Jan Achterhold, Michael Moeller, Jörg Stückler, Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics , International Journal of Computer Vision, 2021.
Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein, Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching, ICLR 2021. (Preprint)
2020
Marcel Seelbach Benkner, Vladislav Golyanik, Christian Theobalt, and Michael Moeller. Adiabatic quantum graph matching with permutation matrix constraints. 3DV 2020. (Preprint)
Hartmut Bauermeister, Martin Burger, Michael Moeller, Learning Spectral Regularizations for Linear Inverse Problems. Accepted at the NeurIPS 2020 Workshop on Deep Learning and Inverse Problems. (Paper)
Paramanand Chandramouli, Kanchana Vaishnavi Gandikota, Andreas Goerlitz, Andreas Kolb, Michael Moeller, A Generative Model for Generic Light Field Reconstruction. Accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (Preprint, Paper)
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, Michael Moeller, Inverting Gradients -- How easy is it to break privacy in federated learning? NeurIPS 2020 (Preprint)
Marco Fumero, Michael Möller, Emanuele Rodola, Nonlinear Spectral Geometry Processing via the TV Transform, SIGGRAPH Asia 2020.
Rama Krishna Kandukuri, Jan Achterhold, Michael Moeller, Jörg Stückler, Learning to Identify Physical Parameters from Video Using Differentiable Physics, Best Paper honorable mention at GCPR 2020. (Preprint).
Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister, Michael Moeller, Fast Convex Relaxations using Graph Discretizations. Accepted for oral presentation at BMVC 2020 (Preprint)
Christina Runkel, Stefan Dorenkamp, Hartmut Bauermeister, Michael Moeller, Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction. Accepted at ICPR 2020 (Preprint)
Guruprasad Hegde, Avinash Nittur Ramesh, Kanchana Vaishnavi Gandikota, Roman Obermaisser, Michael Moeller, A Simple Domain Shifting Networkfor Generating Low Quality Images, Accepted at ICPR 2020 (Preprint)
Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein, Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory. Accepted at ICLR 2020 (Preprint)
2019
Hendrik Sommerhoff, Andreas Kolb, Michael Moeller, Energy Dissipation with Plug-and-Play Priors, Accepted at NeurIPS 2019 Workshop on Solving Inverse Problems with Deep Networks. (Paper)
Jonas Geiping, Michael Moeller, Parametric Majorization for Data-Driven Energy Minimization Methods, Accepted at ICCV 2019 (Preprint)
Michael Moeller, Thomas Möllenhoff, Daniel Cremers. Controlling Neural Networks via Energy Dissipation. Accepted at ICCV 2019 (Preprint)
Tak Ming Wong, Matthias Kahl, Peter Haring Bolívar, Andreas Kolb, Michael Moeller, Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction. Accepted at GCPR 2019 (Preprint)
2018
Michael Moeller, Daniel Cremers. Image Denoising - Old and New. Invited book chapter to be published with Springer. (Preprint)
Jonas Geiping, Michael Moeller. Composite Optimization by Nonconvex Majorization-Minimization. Accepted at SIAM J. on Imaging Sciences. (Preprint, Paper)
Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller. Lifting Layers: Analysis and Applications. Oral presentation at ECCV 2018. (Preprint)
Rania Briq, Michael Moeller, Jürgen Gall. Convolutional Simplex Projection Network for Weakly Supervised Semantic Segmentation. Accepted at BMVC 2018.
Michael Moeller, Otmar Loffeld, Jürgen Gall, Felix Krahmer. Are good local minima wide in sparse recovery? Accepted at CoSeRa 2018. (Preprint)
Florian Bernard, Christian Theobalt, Michael Moeller. Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems. Accepted at CVPR 2018. (Preprint)
Thomas Frerix*, Thomas Möllenhoff*, Michael Moeller*, Daniel Cremers. Proximal Backpropagation. Accepted at ICLR 2018. (Preprint). (*equal contribution)
Mai Lan Ha, Gianni Franchi, Michael Moeller, Andreas Kolb, Volker Blanz. Segmentation and Shape Extraction from Convolutional Neural Networks. Accepted at IEEE WACV 2018.
2017
Jonas Geiping, Hendrik Dirks, Daniel Cremers, Michael Moeller. Multiframe Motion Coupling via Infimal Convolution Regularization for Video Super Resolution. EMMCVPR 2017. (Preprint)
Tim Meinhardt, Michael Moeller, Caner Hazirbas, Daniel Cremers. Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems. ICCV 2017. (Preprint)
Emanuele Rodola, Michael Moeller, Daniel Cremers. Regularized Point-wise Map Recovery from Functional Correspondence. Computer Graphics Forum, pp. 700-711, vol. 36(8), 2017.
Björn Bringmann, Daniel Cremers, Felix Krahmer, Michael Moeller. The Homotopy Method Revisited: Computing Solution Paths of l^1-Regularized Problems. Mathematics of Computation, published electronically. (Preprint)
Martin Benning*, Michael Moeller*, Raz Nossek*, Martin Burger, Daniel Cremers, Guy Gilboa, Carola Schönlieb, Nonlinear Spectral Image Fusion. SSVM 2017. (Preprint) (*equal contribution)
2016
Emanuel Laude, Thomas Möllenhoff, Michael Moeller, Jan Lellmann, Daniel Cremers. Convex Relaxation of Sublabel-Accurate Vectorial Multilabel Energies. ECCV 2016. (Preprint)
Martin Burger*, Guy Gilboa*, Michael Moeller*, Lina Eckardt, Daniel Cremers. Spectral Decompositions using One-Homogeneous Functionals. SIAM J. on Imaging Sciences, pp. 1374--1408, vol. 9(3), 2016. (Preprint) (*equal contribution)
Guy Gilboa, Michael Moeller, Martin Burger. Nonlinear Spectral Analysis via One-homogeneous Functionals - Overview and Future Prospects. Journal of Mathematical Imaging and Vision, pp. 300-319, vol. 56, issue 2, 2016. (Preprint, Paper)
Thomas Möllenhoff, Emanuel Laude, Michael Moeller, Jan Lellmann, Daniel Cremers. Sublabel-accurate Relaxation of Nonconvex Energies. Best paper honorable mention at CVPR 2016. (Preprint)
Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers. Collaborative Total Variation: A General Framework for Vectorial TV Models. SIAM J. on Imaging Sciences, pp. 116-151, vol. 9(1), 2016. (Paper, Preprint).
Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers. On the Implementation of Collaborative Total Variation Regularization: Application to Cartoon+Texture Decomposition. IPOL, vol. 6, pp. 27-74, 2016. (Paper)
Michael Moeller, Xiaoqun Zhang. Fast Sparse Reconstruction: Greedy Inverse Scale Space Flows. Mathematics of Computations, pp. 179-208, vol. 85, 2016. (Preprint)
2015
Michael Moeller, Julia Diebold, Guy Gilboa, Daniel Cremers. Learning Nonlinear Spectral Filters for Color Image Reconstruction. IEEE ICCV, pp. 289-297, 2015. (Paper)
Emanuele Rodolà, Michael Moeller, Daniel Cremers. Point-wise Map Recovery and Refinement from Functional Correspondence. Best paper award. VMV 2015. (Preprint)
Michael Moeller, Martin Benning, Carola Schoenlieb, Daniel Cremers. Variational Depth from Focus Reconstruction. IEEE Trans. on Imag. Proc., pp. 5369-5378, vol. 24(12), 2015. (Preprint, Paper)
Pia Heins, Michael Moeller, Martin Burger. Locally Sparse Reconstruction Using ell^{1,\infty} Norms. Inverse Problems and Imaging, pp. 1093-1137, vol 9(4), 2015. (Preprint)
Martin Burger, Lina Eckardt, Guy Gilboa, Michael Moeller. Spectral Representation of One-Homogeneous Functionals. SSVM, pp. 16-27, vol. 9087, 2015. (Preprint, Paper)
Julia Diebold, Nikolaus Demmel, Caner Hazirbas, Michael Moeller, Daniel Cremers. Interactive Multilabel Segmentation of RGB-D Images. SSVM, pp. 294--306, vol. 9087, 2015. (Paper)
Thomas Moellenhoff, Evgeny Strekalovskiy, Michael Moeller, Daniel Cremers. The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings. SIAM J. on Imaging Sciences, pp. 827-857, vol. 8(3), 2015. (Preprint, Paper)
Joan Duran Grimalt, Michael Moeller, Catalina Sbert, Daniel Cremers. A Framework for Nonlocal Vectorial Total Variation based on $\ell^{p,q,r}$-norms. EMMCVPR Lecture Notes in Computer Sci., pp. 141-154, vol. 8932, 2015. (Paper)
Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Moeller, Daniel Cremers. Low Rank Priors for Regularization of Color Images. EMMCVPR Lecture Notes in Computer Sci., pp. 126--140, vol. 8932, 2015. (Preprint, Paper).
2014
Michael Moeller, Eva Maria Brinkmann, Martin Burger, Tamara Seybold. Color Bregman TV. SIAM J. on Imaging Sciences, pp. 2771-2806, vol. 7(4), 2014. (Preprint, Paper)
Michael Moeller, Martin Burger, Peter Dieterich, Albrecht Schwab. A Framework for Automated Cell Tracking in Phase Contrast Microscopic Videos based on Normal Velocities. Elsevier Journal of Visual Communication and Image Representation, pp. 396-409, vol. 25(2), 2014. (Paper, Preprint)
2013
Michael Moeller, Martin Burger. Multiscale Methods for Polyhedral Regularizations. SIAM J. on Optim., pp. 1424-1456, vol. 23, 2013. (Paper, Preprint)
Martin Burger, Michael Moeller, Martin Benning, Stanley Osher. An Adaptive Inverse Scale Space Method for Compressed Sensing. Mathematics of Computation, pp. 269-299, vol. 82, 2013. (Paper, Preprint)
Yi Yang, Michael Moeller, Stanley Osher. A Dual Split Bregman Method for Fast l1 Minimization. Mathematics of Computation, pp. 2061-2085, vol. 82, 2013. (Paper, Preprint)
2012
Michael Moeller, Todd Wittman, Andrea Bertozzi, Martin Burger. A Variational Approach for Sharpening High Dimensional Images. SIAM J. on Imaging Sciences, pp. 150-178, vol. 5, 2012. (Paper)
Ernie Esser, Michael Moeller, Stanley Osher, Guillermo Sapiro and Jack Xin. A Convex Model for Matrix Factorization and Dimensionality Reduction on Physical Space and Its Application to Blind Hyperspectral Unmixing. IEEE Trans. on Image Processing. pp. 3239-3252, vol. 21(7), 2013. (Paper, Preprint)
Michael Moeller. The adaptive Inverse Scale Space Method for Hyperspectral Unmixing. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 7492 - 7495, 2012. (Paper)
2010
Sheida Rahmani, Melissa Strait, Daria Merkurjev, Michael Moeller, Todd Wittman. An Adaptive IHS Pan-sharpening Method. IEEE Letters on Geoscience and Remote Sensing, pp. 746 - 750, vol. 7(4), 2010. (Paper)
2009