Adobe, Inc.

Sarah Stuckey

Elya Shechtman

Sohrab Amirghodsi

Betty Leong

Zhe Lin

Jianming Zhang

Sarah Kong

Alan Lee Erickson

I-Ming Pao

Bradee Rae Evans

The present disclosure relates to systems, method, and computer readable media that iteratively apply a neural network to a digital image at a reduced resolution to automatically identify pixels of salient objects portrayed within the digital image. For example, the disclosed systems can generate a reduced-resolution digital image from an input digital image and apply a neural network to identify a region corresponding to a salient object. The disclosed systems can then iteratively apply the neural network to additional reduced-resolution digital images (based on the identified region) to generate one or more reduced-resolution segmentation maps that roughly indicate pixels of the salient object. In addition, the systems described herein can perform post-processing based on the reduced-resolution segmentation map(s) and the input digital image to accurately determine pixels that correspond to the salient object.

Iteratively applying neural networks to automatically identify pixels of salient objects portrayed in digital images

Embodiments of the present invention provide systems, methods, and computer storage media for automatically synthesizing a content-aware fill using similarity transformed patches. A user interface receives a user-specified hole and a user-specified sampling region, both of which may be stored in a constraint mask. A brush tool can be used to interactively brush the sampling region and modify the constraint mask. The mask is passed to a patch-based synthesizer configured to synthesize the fill using similarity transformed patches sampled from the sampling region. Fill properties such as similarity transform parameters can be set to control the manner in which the fill is synthesized. A live preview can be provided with gradual updates of the synthesized fill prior to completion. Once a fill has been synthesized, the user interface presents the original image, replacing the hole with the synthesized fill.

Previewing a content-aware fill

Interactive system for automatically synthesizing a content-aware fill

In some embodiments, an image editing application stores, based on a first selection input, a selection state that identifies a first image portion of a target image as included in a preview image displayed in a mask-based editing interface of the image editing application. An edit to the preview image generated from the selected first image portion is applied in the mask-based editing interface. The image editing application also updates an edit state that tracks the edit applied to the preview image. The image editing application modifies, based on a second selection input received via the mask-based editing interface, the selection state to include a second image portion in the preview image. The edit state is maintained with the applied edit concurrently with modifying the selection state. The image editing application applies the edit to the modified preview image in the mask-based editing interface.

Editing dynamically selected portions of target images in a mask-based editing interface

Growing community of inventors

Petaluma, CA, United States of America

Sarah Stuckey