3 papers
math.NA2026
Data-Consistent Learning of Inverse Problems
Markus Haltmeier, Gyeongha Hwang
Inverse problems are inherently ill-posed, suffering from non-uniqueness and instability. Classical regularization methods provide mathematically well-founded solutions, ensuring s…
cs.CV2026
HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training
Markus Haltmeier, Lukas Neumann, Nadja Gruber +2
Solving image reconstruction problems of the form \(\mathbf{A} \mathbf{x} = \mathbf{y}\) remains challenging due to ill-posedness and the lack of large-scale supervised datasets. D…
cs.CV2025
Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated Noise
Nadja Gruber, Johannes Schwab, Markus Haltmeier +3
We propose Noisier2Inverse, a correction-free self-supervised deep learning approach for general inverse problems. The proposed method learns a reconstruction function without the…