Abstract: Machine learning video resolution adjustment techniques are described. An input digital video is received having a plurality of frames and processed by one or more machine-learning models using a processing device. The processing is performed such that the input digital video having frames in a first resolution is adjusted into an output digital video having the frames in a second resolution. Examples of processing include use of a flow guided feature propagation module, anti-aliasing blocks, and/or a high-frequency shuttle.

Abstract: Repeated distractor detection techniques for digital images are described. In an implementation, an input is received by a distractor detection system specifying a location within a digital image, e.g., a single input specifying a single set of coordinates with respect to a digital image. An input distractor is identified by the distractor detection system based on the location, e.g., using a machine-learning model. At least one candidate distractor is detected by the distractor detection system based on the input distractor, e.g., using a patch-matching technique. The distractor detection system is then configurable to verify that the at least one candidate distractor corresponds to the input distractor. The verification is performed by comparing candidate distractor image features extracted from the at least one candidate distractor with input distractor image features extracted from the input distractor.

Abstract: Techniques for performing a digital operation on a digital image are described along with methods and systems employing such techniques. According to the techniques, an input (e.g., an input stroke) is received by, for example, a processing system. Based upon the input, an area of the digital image upon which a digital operation (e.g., for removal of a distractor within the area) is to be performed is determined. In an implementation, one or more metrics of an input stroke are analyzed, typically in real time, to at least partially determine the area upon which the digital operation is to be performed. In an additional or alternative implementation, the input includes a first point, a second point and a connector, and the area is at least partially determined by a location of the first point relative to a location of the second point and/or by locations of the first point and/or second point relative to one or more edges of the digital image.

Abstract: Inpainting dispatch techniques for digital images are described. In one or more examples, an inpainting system includes a plurality of inpainting modules. The inpainting modules are configured to employ a variety of different techniques, respectively, as part of performing an inpainting operation. An inpainting dispatch module is also included as part of the inpainting system that is configured to select which of the plurality of inpainting modules are to be used to perform an inpainting operation for one or more regions in a digital image, automatically and without user intervention.

Abstract: Various disclosed embodiments are directed to changing parameters of an input image or multidimensional representation of the input image based on a user request to change such parameters. An input image is first received. A multidimensional image that represents the input image in multiple dimensions is generated via a model. A request to change at least a first parameter to a second parameter is received via user input at a user device. Such request is a request to edit or generate the multidimensional image in some way. For instance, the request may be to change the light source position or camera position from a first set of coordinates to a second set of coordinates.

Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

Abstract: Various disclosed embodiments are directed to inpainting one or more portions of a target image based on merging (or selecting) one or more portions of a warped image with (or from) one or more portions of an inpainting candidate (e.g., via a learning model). This, among other functionality described herein, resolves the inaccuracies of existing image inpainting technologies.

Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

Abstract: One example method involves operations for receiving a request to transform an input image into a target image. Operations further include providing the input image to a machine learning model trained to adapt images. Training the machine learning model includes accessing training data having a source domain of images and a target domain of images with a target style. Training further includes using a pre-trained generative model to generate an adapted source domain of adapted images having the target style. The adapted source domain is generated by determining a rate of change for parameters of the target style, generating weighted parameters by applying a weight to each of the parameters based on their respective rate of change, and applying the weighted parameters to the source domain. Additionally, operations include using the machine learning model to generate the target image by modifying parameters of the input image using the target style.

Abstract: Example-based edge-aware directional texture painting techniques are described. Inputs are received that define a target direction field and a plurality of edges as part of a target shape mask. A texture is synthesized from a source image by the computing device to be applied to the set of pixels of the target mask using a source shape mask and a source direction field. The source shape mask defines a plurality of edges of the source mask such that the synthesized texture applied to the plurality of edges of the target shape mask correspond to respective ones of the plurality of edges of the source shape mask. The source direction field is taken from the source image such that the synthesized texture applied to the target direction field corresponds to the source direction field. The pixels in the user interface are painted by the computing device using the synthesized texture.

Abstract: Example-based edge-aware directional texture painting techniques are described. Inputs are received that define a target direction field and a plurality of edges as part of a target shape mask. A texture is synthesized from a source image by the computing device to be applied to the set of pixels of the target mask using a source shape mask and a source direction field. The source shape mask defines a plurality of edges of the source mask such that the synthesized texture applied to the plurality of edges of the target shape mask correspond to respective ones of the plurality of edges of the source shape mask. The source direction field is taken from the source image such that the synthesized texture applied to the target direction field corresponds to the source direction field. The pixels in the user interface are painted by the computing device using the synthesized texture.

Abstract: Example-based edge-aware directional texture painting techniques are described. Inputs are received that define a target direction field and a plurality of edges as part of a target shape mask. A texture is synthesized from a source image by the computing device to be applied to the set of pixels of the target mask using a source shape mask and a source direction field. The source shape mask defines a plurality of edges of the source mask such that the synthesized texture applied to the plurality of edges of the target shape mask correspond to respective ones of the plurality of edges of the source shape mask. The source direction field is taken from the source image such that the synthesized texture applied to the target direction field corresponds to the source direction field. The pixels in the user interface are painted by the computing device using the synthesized texture.

Abstract: Example based edge-aware directional texture painting techniques are described. Inputs are received that define a target direction field and a plurality of edges as part of a target shape mask. A texture is synthesized from a source image by the computing device to be applied to the set of pixels of the target mask using a source shape mask and a source direction field. The source shape mask defines a plurality of edges of the source mask such that the synthesized texture applied to the plurality of edges of the target shape mask correspond to respective ones of the plurality of edges of the source shape mask. The source direction field is taken from the source image such that the synthesized texture applied to the target direction field corresponds to the source direction field. The pixels in the user interface are painted by the computing device using the synthesized texture.