Search Results for author: Thomas Köhler

Found 12 papers, 2 papers with code

LORD: Leveraging Open-Set Recognition with Unknown Data

no code implementations24 Aug 2023 Tobias Koch, Christian Riess, Thomas Köhler

To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique.

Open Set Learning

Merging-ISP: Multi-Exposure High Dynamic Range Image Signal Processing

no code implementations12 Nov 2019 Prashant Chaudhari, Franziska Schirrmacher, Andreas Maier, Christian Riess, Thomas Köhler

As such, it is end-to-end trainable, circumvents the use of hand-crafted and potentially complex algorithms, and mitigates error propagation.

Demosaicking Vocal Bursts Intensity Prediction

Multi-Frame Super-Resolution Reconstruction with Applications to Medical Imaging

no code implementations21 Dec 2018 Thomas Köhler

The optical resolution of a digital camera is one of its most crucial parameters with broad relevance for consumer electronics, surveillance systems, remote sensing, or medical imaging.

Multi-Frame Super-Resolution

Benchmarking Super-Resolution Algorithms on Real Data

no code implementations8 Sep 2017 Thomas Köhler, Michel Bätz, Farzad Naderi, André Kaup, Andreas K. Maier, Christian Riess

Therefore, current studies are either evaluated 1) on simulated data or 2) on real data without a pixel-wise ground truth.

Benchmarking Super-Resolution

QuaSI: Quantile Sparse Image Prior for Spatio-Temporal Denoising of Retinal OCT Data

no code implementations8 Mar 2017 Franziska Schirrmacher, Thomas Köhler, Lennart Husvogt, James G. Fujimoto, Joachim Hornegger, Andreas K. Maier

Optical coherence tomography (OCT) enables high-resolution and non-invasive 3D imaging of the human retina but is inherently impaired by speckle noise.

Denoising

Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

no code implementations6 Sep 2016 Cosmin Bercea, Andreas Maier, Thomas Köhler

Motion estimation across low-resolution frames and the reconstruction of high-resolution images are two coupled subproblems of multi-frame super-resolution.

Image Reconstruction Motion Estimation +1

Super-Resolved Retinal Image Mosaicing

no code implementations10 Feb 2016 Thomas Köhler, Axel Heinrich, Andreas Maier, Joachim Hornegger, Ralf P. Tornow

The acquisition of high-resolution retinal fundus images with a large field of view (FOV) is challenging due to technological, physiological and economic reasons.

Cannot find the paper you are looking for? You can Submit a new open access paper.