Adobe, Inc.

Sunil Kumar

Saikat Chakrabarty

Saumitra Sharma

The disclosure describes one or more embodiments of systems, methods, and non-transitory computer-readable media that generate a transferred hairstyle image that depicts a person from a source image having a hairstyle from a target image. For example, the disclosed systems utilize a face-generative neural network to project the source and target images into latent vectors. In addition, in some embodiments, the disclosed systems quantify (or identify) activation values that control hair features for the projected latent vectors of the target and source image. Furthermore, in some instances, the disclosed systems selectively combine (e.g., via splicing) the projected latent vectors of the target and source image to generate a hairstyle-transfer latent vector by using the quantified activation values. Then, in one or more embodiments, the disclosed systems generate a transferred hairstyle image that depicts the person from the source image having the hairstyle from the target image by synthesizing the hairstyle-transfer latent vector.

Transferring hairstyles between portrait images utilizing deep latent representations

Systems and methods for digital image processing are described. Embodiments of the systems and methods includes identifying a digital image that includes an obscured region; generating a predicted image using a neural network comprising an encoder, a feature transfer network, and a decoder, wherein the feature transfer network is trained to predict features corresponding to the obscured region based on an output of the decoder; and combining the digital image and the predicted image to produce a reconstructed version of the digital image including details corresponding to the obscured region that are not present in the digital image.

Facial reconstruction network

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images of modified resolution by filtering in the frequency domain. For example, the disclosed systems can utilize a tiling procedure to generate discrete cosine transform blocks. The disclosed systems can further filter the quantized data of the discrete cosine transform blocks within the frequency domain using, for example, a Lanczos resampling kernel. In addition, the digital image resolution modification system can utilize sub-band approximation and block composition to generate a modified digital image.

Growing community of inventors

Mathura, India

Sunil Kumar