Adobe, Inc.

Lucasfilm Entertainment Company Ltd.

Ian D Sachs

Brian Lynn Price

Elya Shechtman

Sylvain Philippe Paris

Aaron Phillip Hertzmann

Xiaoyong Shen

Daniel Goldman

Nicholas Grant Rasmussen

Ronen Barzel

Robert Bailey

Probabilistic determination of selected image portions is described. In one or more implementations, a selection input is received for selecting a portion of an image. For pixels of the image that correspond to the selection input, probabilities are determined that the pixels are intended to be included as part of a selected portion of the image. In particular, the probability that a given pixel is intended to be included as part of the selected portion of the image is determined as a function of position relative to center pixels of the selection input as well as a difference in one or more visual characteristics with the center pixels. The determined probabilities can then be used to segment the selected portion of the image from a remainder of the image. Based on the segmentation of the selected portion from the remainder of the image, selected portion data can be generated that defines the selected portion of the image.

Probabilistic determination of selected image portions

Systems and methods are disclosed for segregating target individuals represented in a probe digital image from background pixels in the probe digital image. In particular, in one or more embodiments, the disclosed systems and methods train a neural network based on two or more of training position channels, training shape input channels, training color channels, or training object data. Moreover, in one or more embodiments, the disclosed systems and methods utilize the trained neural network to select a target individual in a probe digital image. Specifically, in one or more embodiments, the disclosed systems and methods generate position channels, training shape input channels, and color channels corresponding the probe digital image, and utilize the generated channels in conjunction with the trained neural network to select the target individual.

Utilizing deep learning for automatic digital image segmentation and stylization

Techniques for focal length warping are described. Focal length warping, for instance, may provide an automated approach for correcting distortion in an input image to improve its perceptual quality. In at least some implementations, a focal length of a camera lens used to capture an image and an estimated camera distance are utilized to three-dimensionally reproject and warp the image to generate an adjusted image simulating a new focal length and a new camera distance. Implementations of focal length warping may estimate a camera distance based on facial features in an image.

Focal length warping

Techniques are disclosed for automatically transferring a style of at least two reference images to an input image. The resulting transformation of the input image matches the visual styles of the reference images without changing the identity of the subject of the input image. Each image is decomposed into levels of detail with corresponding energy levels and a residual. A style transfer operation is performed at each energy level and residual using the reference image that most closely matches the input image at each energy level. The transformations of each level of detail and the residual of the input image are aggregated to generate an output image having the styles of the reference images. In some cases, the transformations are performed on the foreground of the input image, and the background can be transformed by an amount that is proportional to the aggregated transformations of the foreground.

Style transfer for headshot portraits

A system includes a computing device that includes a memory configured to store instructions. The computing device also includes a processor configured to execute the instructions to perform a method that includes defining a simulated fluid object that includes a first portion and a second portion being represented by a signed distance function. The method also includes applying at least one constraint to the first portion of the simulated fluid object to match a velocity of a target. The method also includes applying a collection of calculated forces to the second portion of the simulated fluid object. Also, the method includes rendering the first portion applied with the at least one constraint and the second portion applied with the collection of calculated forces to present the simulated fluid object.

Growing community of inventors

San Francisco, CA, United States of America

Ian D Sachs