Canva Pty Ltd

Sanchit Sanchit

Stefan Paul Sietzen

Alexander Tack

Paul Angerer

Methods of training a machine learning model for image processing are described, as well as methods for image processing to determine a predicted rotation value for an image based on the trained machine learning model. A method of training includes utilising as a learning objective a reduction or minimisation of a classification loss. Training image pairs may be associated with classifications corresponding to rotation values for the purpose of determining the classification loss. An image may be divided into a plurality of images for determining an input to the machine learning model, for training or for image processing.

Image rotation

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.

Methods and systems for prompt-based image editing

Described herein is a computer implemented method for automatically generating a cropped version of an input image. The method includes processing the input image to detect a salient region of the input image and generating a set of crop candidates based on the salient region of the input image, each crop candidate defining a different image crop. A set of candidate scores is calculated, each corresponding to a crop candidate, and a first crop candidate is selected based on the set of scores. The cropped version of the input image is then generated based on the image crop defined by the first crop candidate.

Growing community of inventors

Vienna, Austria

Sanchit Sanchit