CPC Class G06T

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output image. In one aspect, one of the methods includes generating the output image intensity value by intensity value according to a generation order of pixel—color channel pairs from the output image, comprising, for each particular generation order position in the generation order: generating a current output image representation of a current output image, processing the current output image representation using a decoder neural network to generate a probability distribution over possible intensity values for the pixel—color channel pair at the particular generation order position, wherein the decoder neural network includes one or more local masked self-attention sub-layers; and selecting an intensity value for the pixel—color channel pair at the particular generation order position using the probability distribution.

In implementations of correcting dust and scratch artifacts in digital images, an artifact correction system receives a digital image that depicts a scene and includes a dust or scratch artifact. The artifact correction system generates, with a generator of a generative adversarial neural network (GAN), a feature map from the digital image that represents features of the dust or scratch artifact and features of the scene. A training system can train the generator adversarially to reduce visibility of dust and scratch artifacts in digital images against a discriminator, and train the discriminator to distinguish between reconstructed digital images generated by the generator and real-world digital images. The artifact correction system generates, from the feature map and with the generator, a reconstructed digital image that depicts the scene of the digital image and reduces visibility of the dust or scratch artifact of the digital image.

Aspects of the present disclosure include methods, systems, and non-transitory computer readable media that perform the steps of receiving a first plurality of snapshots, generating a first plurality of descriptors each associated with the first plurality of snapshots, grouping the first plurality of snapshots into at least one cluster based on the plurality of descriptors, selecting a representative snapshot for each of the at least one cluster, generating at least one second descriptor for the representative snapshot for each of the at least one cluster, wherein the at least one second descriptor is more complex than the first plurality of descriptors, and identifying a target by applying the at least second descriptor to a second plurality of snapshots.