Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

Abstract: The present disclosure refers to transfer line exchangers with improved cooling capacity, equipped with a thermal spray coating in crackers and a method for the maintenance of transfer line exchangers with the help of a thermal spray coating. In some embodiments, the thermal spray coating is obtained from a spray material formed of Cr3C2 and a NiCr alloy. Preferably, the spray coating material comprises at least 60 wt.-%, preferably at least 70 wt.-% of Cr3C2, based on the total weight of the spray material.

Abstract: A method for cleaning a metal surface of a metal component of an industrial plant is disclosed comprising measuring the electrical resistance RA1 of a metal component over a cleaned area of the metal surface with a resistance meter, comparing the electrical resistance RA1 measured with a pre-determined electrical resistance value RDET, assessing whether RA1 is greater, smaller or equal to RDET, and repeating cleaning if the electrical resistance RA1 measured is greater than RDET, or terminating cleaning of the surface area of the metal component if RA1 is smaller than or identical to RDET.

Abstract: Methods of detecting carburization, nitriding or chromium depletion in a non- or weakly ferromagnetic test object using a permanent magnet having a magnet pull force equal to or greater than about 75N and measuring either the adhesive force to detach the magnet from the test object or the attractive force in which the magnet is being pulled towards the surface of the test object.

Abstract: A method for cleaning a metal surface of a metal component of an industrial plant is disclosed comprising measuring the electrical resistance RA1 of a metal component over a cleaned area of the metal surface with a resistance meter, comparing the electrical resistance RA1 measured with a pre-determined electrical resistance value RDET, assessing whether RA1 is greater, smaller or equal to RDET, and repeating cleaning if the electrical resistance RA1 measured is greater than RDET, or terminating cleaning of the surface area of the metal component if RA1 is smaller than or identical to RDET.

Abstract: Methods of detecting carburization, nitriding or chromium depletion in a non- or weakly ferromagnetic test object using a permanent magnet having a magnet pull force equal to or greater than about 75N and measuring either the adhesive force to detach the magnet from the test object or the attractive force in which the magnet is being pulled towards the surface of the test object.