Abstract: Methods of training a machine learning model for image processing are described. A method of training includes utilising as a learning objective a reduction or minimisation of a combination of both an image loss and a classification loss. A method of training includes utilising unsupervised images pairs generated by applying a selected degradation model to a target image, the selected degradation model being selected based on classification information associated with the target image. Methods for generating unsupervised image pairs and methods for image processing using a trained machine learning model are also described, together with computer systems and computer-readable storage for performing the various methods.

Abstract: Described embodiments generally relate to a method of generating an image editing tool recommendation. The method includes receiving a prompt entered by a user; processing the prompt using a tool class prediction model to predict a tool class associated with the prompt, wherein the tool class is associated with at least one image editing tool that is configured to perform an image editing function described by the prompt; determining an image editing tool associated with the predicted tool class; and outputting a recommendation to the user directing the user to the determined image editing tool.

Abstract: Described herein is a computer implemented method including displaying an image on a display and then processing, using one or more processing units, the image to identify one or more primary object regions in the image. The method further includes receiving a first user input selecting a first input image position, determining that the first input image position does not correspond to any primary object region, and in response to determining that the first input image position does not correspond to any primary object region, processing the image based on the first input image position to identify a secondary object region in the image.

Abstract: Methods of training a machine learning model for image processing are described. A method of training includes utilising as a learning objective a reduction or minimisation of a combination of both an image loss and a classification loss. A method of training includes utilising unsupervised images pairs generated by applying a selected degradation model to a target image, the selected degradation model being selected based on classification information associated with the target image. Methods for generating unsupervised image pairs and methods for image processing using a trained machine learning model are also described, together with computer systems and computer-readable storage for performing the various methods.

Abstract: Image processing techniques are described, including techniques in which text data associated with an image is used to determine a font of text in an image. The image is split into a plurality of crops based on the text data. A trained machine learning model is used to determine feature vectors of the image. The feature vectors are combined into a combined feature vector. A second trained machine learning model is used to determine a font using the combined feature vector. The second trained machine learning model may be a multi-layer perceptron network. The second trained machined learning model may be trained on a plurality of images with text of known fonts and properties. The described image processing techniques also include text removal.

Abstract: Methods of training a machine learning model for image processing are described. A method of training includes utilising as a learning objective a reduction or minimisation of a combination of both an image loss and a classification loss. A method of training includes utilising unsupervised images pairs generated by applying a selected degradation model to a target image, the selected degradation model being selected based on classification information associated with the target image. Methods for generating unsupervised image pairs and methods for image processing using a trained machine learning model are also described, together with computer systems and computer-readable storage for performing the various methods.

Abstract: Described embodiments generally relate to a computer-implemented method for editing an image. The method includes accessing an image; identifying at least a first area of the image and a second area of the image; configuring a model to generate an edited image based on the first area of the image and the second area of the image, wherein the edited image comprises a first area of the edited image and a second area of the edited image; wherein the model is configured to generate the edited image such that the first area of the edited image differs from the first area of the image less than the second area of the edited image differs from the second area of the image.

Abstract: Described embodiments generally relate to a computer-implemented method for performing inpainting. The method includes accessing a first image; receiving a selected area of the first image; identifying a foreground area of the first image; generating a merged mask based on the union of the user selected area and the foreground area; performing an inpainting process on the area of the first image corresponding to the merged mask to generate a second image, being an inpainted image; generating a reduced mask based on the user selected area reduced by the foreground area; and combining the first image with the area of the second image corresponding to the reduced mask to produce an output image.

Abstract: Some embodiments relate to a method of performing prompt-based image editing. The method includes accessing an image; receiving a selected area of the image; receiving a prompt, wherein the prompt is indicative of an editing instruction; generating a latent by transforming the image into visual noise; predicting, based on the latent and the prompt, a noise image corresponding to the latent; subtracting at least a portion of the noise image from the latent to generate an updated latent; generating a noisy representation of the image; generating a masked latent based on the noisy representation, the updated latent and selected area, wherein the masked latent comprises the updated latent in the areas corresponding to the selected area, and the noisy representation in the areas that do not correspond to the selected area.

Abstract: Described embodiments generally relate to a method of generating an image editing tool recommendation. The method includes receiving a prompt entered by a user; processing the prompt using a tool class prediction model to predict a tool class associated with the prompt, wherein the tool class is associated with at least one image editing tool that is configured to perform an image editing function described by the prompt; determining an image editing tool associated with the predicted tool class; and outputting a recommendation to the user directing the user to the determined image editing tool.

Abstract: Some embodiments relate to a method of performing prompt-based image editing. The method includes accessing an image; receiving a selected area of the image; receiving a prompt, wherein the prompt is indicative of an editing instruction; generating a latent by transforming the image into visual noise; predicting, based on the latent and the prompt, a noise image corresponding to the latent; subtracting at least a portion of the noise image from the latent to generate an updated latent; generating a noisy representation of the image; generating a masked latent based on the noisy representation, the updated latent and selected area, wherein the masked latent comprises the updated latent in the areas corresponding to the selected area, and the noisy representation in the areas that do not correspond to the selected area.

Abstract: Described embodiments generally relate to a computer-implemented method for performing prompt-based inpainting.

Abstract: Described embodiments generally relate to a computer-implemented method for performing inpainting. The method includes accessing a first image; receiving a selected area of the first image; identifying a foreground area of the first image; generating a merged mask based on the union of the user selected area and the foreground area; performing an inpainting process on the area of the first image corresponding to the merged mask to generate a second image, being an inpainted image; generating a reduced mask based on the user selected area reduced by the foreground area; and combining the first image with the area of the second image corresponding to the reduced mask to produce an output image.

Abstract: Methods of training a machine learning model for image processing are described. A method of training includes utilising as a learning objective a reduction or minimisation of a combination of both an image loss and a classification loss. A method of training includes utilising unsupervised images pairs generated by applying a selected degradation model to a target image, the selected degradation model being selected based on classification information associated with the target image. Methods for generating unsupervised image pairs and methods for image processing using a trained machine learning model are also described, together with computer systems and computer-readable storage for performing the various methods.