Tom Dagès

Thomas Dagès

I am a Thomas Bayes postdoctoral fellow at the Munich Center for Machine Learning (MCML) and at the Technical University of Munich (TUM) (Munich, Germany) in the Computer Vision Group (CVG) supervised by Prof. Daniel Cremers. I was previously a postdoctoral fellow in the Geometric Image Processing (GIP) lab at the Technion-Israel Institute of Technology (Haifa, Israel) under the supervision of Prof. Alfred Bruckstein, Prof. Michael Lindenbaum, and Prof. Ron Kimmel. Before that, I was a PhD student in the Computer Science Faculty at the Technion supervised by Prof. Alfred Bruckstein and Prof. Michael Lindenbaum. I previously obtained my M.Sc. in Computer Science from the Technion, and my Diplôme d'Ingénieur (MSc equivalent) from École polytechnique (Saclay, France).

My research interests include regular and geometric computer vision, signal and image processing, analysis, and synthesis, and deep learning interpretability.

Email / CV / Google Scholar / Github

Publications

	Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025 [Preprint] [Original preprint] [Poster] [Video] [Code]
	Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding Thomas Dagès, Simon Weber, Ya-Wei Eileen Lin, Ronen Talmon, Daniel Cremers, Michael Lindenbaum, Alfred M. Bruckstein, Ron Kimmel Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [Preprint] [Poster] [Video] [Code]
	Wormhole Loss for Partial Shape Matching Amit Bracha, Thomas Dagès, Ron Kimmel Advances in Neural Information Processing Systems (NeurIPS), 2024 [Preprint] [Poster] [Video] [Code]
	On Unsupervised Partial Shape Correspondence Amit Bracha, Thomas Dagès, Ron Kimmel Proceedings of the Asian conference on computer vision (ACCV), 2024 [Preprint] [Poster] [Code] [PFAUST Dataset]
	A Model is Worth Tens of Thousands of Examples for Estimation and Thousands for Classification Thomas Dagès, Laurent D. Cohen, Alfred M. Bruckstein Pattern Recognition, 2024 [Preprint] [Poster]
	Finsler-Laplace-Beltrami Operators with Application to Shape Analysis Simon Weber, Thomas Dagès, Maolin Gao, Daniel Cremers Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [Preprint] [Poster - Technion CS Graduate Research Day] [Poster - CVPR] [Video]
	A Model is Worth Tens of Thousands of Examples Thomas Dagès, Laurent D. Cohen, Alfred M. Bruckstein International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), 2023 [Preprint] [Poster]
	From Compass and Ruler to Convolution and Nonlinearity: On the Surprising Difficulty of Understanding a Simple CNN Solving a Simple Geometric Estimation Task Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein ArXiv Preprint, 2023 [Poster]
	Doubly Stochastic Pairwise Interactions for Agreement and Alignment Thomas Dagès, Alfred M. Bruckstein SIAM Journal on Applied Mathematics, 2022 [Preprint]
	Probabilistic Gathering of Agents with Simple Sensors Ariel Barel, Thomas Dagès, Rotem Manor, Alfred M. Bruckstein SIAM Journal on Applied Mathematics, 2021 [Preprint] [Code]
	Seeing Things in Random-Dot Videos Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein Asian Conference on Pattern Recognition (ACPR), 2019 [Technical Report]