Learning activation functions in deep (spline) neural networks P Bohra, J Campos, H Gupta, S Aziznejad, M Unser
IEEE Open Journal of Signal Processing 1, 295-309, 2020
26 2020 Continuous-Domain Signal Reconstruction Using P Bohra, M Unser
IEEE Transactions on Signal Processing 68, 4543-4554, 2020
14 2020 Variance-stabilization-based compressive inversion under Poisson or Poisson–Gaussian noise with analytical bounds P Bohra, D Garg, KS Gurumoorthy, A Rajwade
Inverse Problems 35 (10), 105006, 2019
11 * 2019 Learning Lipschitz-controlled activation functions in neural networks for plug-and-play image reconstruction methods P Bohra, D Perdios, A Goujon, S Emery, M Unser
NeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021
10 2021 Approximation of Lipschitz functions using deep spline neural networks S Neumayer, A Goujon, P Bohra, M Unser
SIAM Journal on Mathematics of Data Science 5 (2), 306-322, 2023
5 2023 Bayesian inversion for nonlinear imaging models using deep generative priors P Bohra, T Pham, J Dong, M Unser
IEEE Transactions on Computational Imaging 8, 1237-1249, 2022
3 2022 Computation of" Best" Interpolants in the Lp Sense P Bohra, M Unser
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
3 2020 A Neural-Network-Based Convex Regularizer for Image Reconstruction A Goujon, S Neumayer, P Bohra, S Ducotterd, M Unser
arXiv preprint arXiv:2211.12461, 2022
2 2022 Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions S Ducotterd, A Goujon, P Bohra, D Perdios, S Neumayer, M Unser
arXiv preprint arXiv:2210.16222, 2022
1 2022 Dynamic Fourier ptychography with deep spatiotemporal priors P Bohra, TAM Pham, Y Long, J Yoo, M Unser
Inverse Problems, 2023
2023 A Statistical Framework to Investigate the Optimality of Neural Networks for Inverse Problems P Bohra, PA Pla, JF Giovannelli, M Unser
arXiv preprint arXiv:2203.09920, 2022
2022 POISSON LOW-RANK MATRIX RECOVERY USING THE ANSCOMBE TRANSFORM P Bohra, A Rajwade
2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2018
2018 
Michael UnserProfessor, Biomedical Imaging Group, Ecole Polytechnique Fédérale de Lausanne (EPFL), SwitzerlandAdresse e-mail validée de epfl.ch
