Image segmentation or semantic segmentation is a branch of computer vision that focuses on the division of a digital image into multiple segments (regions or categories) according to its properties and features. This is an extension of image classification in which, in addition to classification, we perform localization for certain classes using a mask. In image segmentation, every pixel in an image is labeled such that pixels with the same label share certain attributes and characteristics and present mask of some class. The Wizart Vision Segmentation API provides the ability to recognize dozens of classes in various combinations, especially for indoor photography. You can solve various tasks such as wall segmentation, floor segmentation, window or door segmentation with just one API call by selecting the appropriate query parameters. Or you can perform only one surface segmentation task within a single request. It depends on your requirement. As a result, you will get a photo with areas filled with different colors depending on the query parameters. Each color corresponds to a certain class.