Abstract: A method for transforming a clothing model image is disclosed. The method receives the clothing model image showing a first person wearing an item of clothing, the first person having a first body shape. The method receives a body shape model for a second person, the second data from a user person having a second body shape. The method determines a warp field for warping the first body shape in the clothing model image to the second body shape. The warp field is determined based on target curves determined from the body shape model for the second person. The method transforms the clothing model image in accordance with the warp field to generate a user warped clothing model image representing the second person wearing the item of clothing A method for determining a body shape model for a person is also disclosed.

Abstract: A computer-implemented method for training a generator to manipulate one or more characteristics of an image is disclosed. The method comprises training a generator to output warp fields that modify one or more characteristics of an image, wherein training the generator comprises use of a Generative Adversarial Network (GAN) and training data comprising a plurality of images.

Abstract: A computer-implemented method evaluates which of a set of reference indicators has colour attributes closest to those of an object. Each respective reference indicator has different colour attributes. The method comprises determining a colour relationship between the object and at least one reference indicator of a first type by analysing a plurality of image portions, each comprising at least part of the object and at least one reference indicator of the first type placed directly on the object. The image portions each have different lighting characteristics. The method also comprises comparing the determined colour relationship to known colour relationships associated with the at least one reference indicator, each known colour relationship representing a relationship between the reference indicator and another reference indicator of the set, to identify which reference indicator of the set has colour attributes closest to those of the object.

Abstract: A computer-implemented method for evaluating which of a set of different types of reference indicator has colour attributes closest to those of an object is disclosed herein. Each respective type of reference indicator has different colour attributes. The method comprises determining a colour relationship between the object and at least one reference indicator of a first type by analysing a plurality of image portions, each image portion comprising at least part of the object and at least one reference indicator of the first type placed directly on the object. The image portions each have different lighting characteristics.