Abstract: Aspects of the present disclosure are directed to systems and methods for generating an inpainting model. The method can include obtaining a plurality of training data items including image and areas to be masked, the areas to be masked including areas of the image input without text. The method can also include fine-tuning a first pre-trained diffusion model to reconstruct masked areas of the image inputs and processing a plurality of first images that comprise text with a fine-tuned version of the first pre-trained diffusion model to generate a plurality of augmented first images. The method can further include fine-tuning a second pre-trained diffusion model using the plurality of first images and the plurality of augmented first images, the second pre-trained diffusion model configured to reconstruct the plurality of synthetic training data items and the second plurality of training data items without mask inputs.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Provided are systems and methods that use generative models (e.g., generative adversarial networks) to enable photorealistic text inpainting in augmented reality. One example application of the proposed systems is to perform augmented reality translation. For example, a user can operate an image capture device (e.g., camera, smartphone, etc.) to capture imagery of a real-world scene that includes real-world text (e.g., signage, restaurant menus, etc.). The real-world text can be translated into a different language. Further, the captured imagery can be processed with a machine-learned generative model to produce an augmented image. The augmented image can depict the real-world scene with the real-world text removed. Specifically, because a machine-learned generative model is used, the augmented image can appear significantly more realistic, for example versus an image in which the real-world text has simply been blocked using a box with a single color.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Provided are systems and methods that use generative models (e.g., generative adversarial networks) to enable photorealistic text inpainting in augmented reality. One example application of the proposed systems is to perform augmented reality translation. For example, a user can operate an image capture device (e.g., camera, smartphone, etc.) to capture imagery of a real-world scene that includes real-world text (e.g., signage, restaurant menus, etc.). The real-world text can be translated into a different language. Further, the captured imagery can be processed with a machine-learned generative model to produce an augmented image. The augmented image can depict the real-world scene with the real-world text removed. Specifically, because a machine-learned generative model is used, the augmented image can appear significantly more realistic, for example versus an image in which the real-world text has simply been blocked using a box with a single color.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.

Abstract: Methods, systems, and apparatus for recognizing objects and providing content related to the recognized objects are described. In one aspect, a method includes detecting presence of one or more objects depicted in a viewfinder of a camera of the mobile device. In response to detecting the presence of the one or more objects, image data representing the one or more objects is sent to a content distribution system that selects content related to objects depicted in images. A location of each of the one or more objects in the viewfinder of the camera is tracked while waiting to receive content from the content distribution system. Content related to the one or more objects is received from the content distribution system. A current location of each object in the viewfinder is determined and the content related to the object is presented within the viewfinder at the current location of the object.