Related papers: Understanding SSIM
With advances in vision and perception architectures, we have realized that working with data is equally crucial, if not more, than the algorithms. Till today, we have trained machines based on our knowledge and perspective of the world.…
Structured Illumination Microscopy (SIM) overcomes the optical diffraction limit by folding high-frequency components into the baseband of the optical system, where they can be extracted and then repositioned to their original location in…
Deep learning models trained with large amounts of data have become a recent and effective approach to predictive problem solving -- these have become known as "foundation models" as they can be used as fundamental tools for other…
Traditional image quality assessment metrics like Mean Squared Error and Structural Similarity Index often fail to reflect perceptual quality under complex distortions. We propose the Hybrid Image Resolution Quality Metric (HIRQM),…
Image metrics predict the perceived per-pixel difference between a reference image and its degraded (e. g., re-rendered) version. In several important applications, the reference image is not available and image metrics cannot be applied.…
The use of deep learning for medical imaging has seen tremendous growth in the research community. One reason for the slow uptake of these systems in the clinical setting is that they are complex, opaque and tend to fail silently. Outside…
Before deploying machine learning models it is critical to assess their robustness. In the context of deep neural networks for image understanding, changing the object location, rotation and size may affect the predictions in non-trivial…
In functional MRI (fMRI), effective connectivity analysis aims at inferring the causal influences that brain regions exert on one another. A common method for this type of analysis is structural equation modeling (SEM). We here propose a…
We propose SADGE, a quantitative similarity metric that predicts the performance of synthetic image datasets for common computer vision tasks without downstream model training. Estimating whether a synthetic dataset will lead to a model…
It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in…
Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media. Despite the…
In this paper, we analyze the behavior of the multivariate symmetric uncertainty (MSU) measure through the use of statistical simulation techniques under various mixes of informative and non-informative randomly generated features.…
Due to common architecture designs, symmetries exist extensively in contemporary neural networks. In this work, we unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine…
Multimodal medical image fusion helps in combining contrasting features from two or more input imaging modalities to represent fused information in a single image. One of the pivotal clinical applications of medical image fusion is the…
Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typically inferior to competing approaches. Most users cannot…
Despite the great advances made in the field of image super-resolution (ISR) during the last years, the performance has merely been evaluated perceptually. Thus, it is still unclear whether ISR is helpful for other vision tasks. In this…
In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image…
Super-resolution, in-painting, whole-image generation, unpaired style-transfer, and network-constrained image reconstruction each include an aspect of machine-learned image synthesis where the actual ground truth is not known at time of…
Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D…
Complex statistical models such as scalar-on-image regression often require strong assumptions to overcome the issue of non-identifiability. While in theory it is well understood that model assumptions can strongly influence the results,…