Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation.
However, it is challenging to analyze the reliability of these CNNs for the image fusion tasks since no groundtruth is available.
The medical image fusion combines two or more modalities into a single view while medical image translation synthesizes new images and assists in data augmentation.
We address a core problem of computer vision: Detection and description of 2D feature points for image matching.
In order to work with wide-baseline light fields, we introduce the idea of EPI-Shift: To virtually shift the light field stack which enables to retain a small receptive field, independent of the disparity range.
Multimodal medical image fusion helps in combining contrasting features from two or more input imaging modalities to represent fused information in a single image.
Life science today involves computational analysis of a large amount and variety of data, such as volumetric data acquired by state-of-the-art microscopes, or mesh data resulting from analysis of such data or simulations.
Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool.
The computation power of supercomputers grows faster than the bandwidth of their storage and network.
Distributed, Parallel, and Cluster Computing
The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w. r. t.
In recent years, the task of estimating the 6D pose of object instances and complete scenes, i. e. camera localization, from a single input image has received considerable attention.
This is done by describing the posterior density of a particular object pose with a convolutional neural network (CNN) that compares an observed and rendered image.