Adobe, Inc.

Realtek Semiconductor Inc.

Sony Corporation

Sony Electronics Inc

I-Ming Pao

Sarah Kong

Alan Lee Erickson

Zhe Lin

Hyunghwan Byun

Hailin Jin

Zhaowen Wang

Betty Leong

Jianming Zhang

Xiaohui Shen

Kalyan Krishna Sunkavalli

Xin Lu

Yuyan Song

Song Jin

Guotong Feng

Yingcong Chen

Jue Wang

Yun Gong

Yung-Chin Chen

Yang Liu

Sarah Stuckey

Seth Shaw

Yukie Takahashi

Ke Ma

Frederick Mandia

Meredith Payne Stotzner

Quynn Megan Le

Methods and systems are provided for generating enhanced image. A neural network system is trained where the training includes training a first neural network that generates enhanced images conditioned on content of an image undergoing enhancement and training a second neural network that designates realism of the enhanced images generated by the first neural network. The neural network system is trained by determine loss and accordingly adjusting the appropriate neural network(s). The trained neural network system is used to generate an enhanced aesthetic image from a selected image where the output enhanced aesthetic image has increased aesthetics when compared to the selected image.

Aesthetics-guided image enhancement

The present disclosure provides systems and methods for image editing. Embodiments of the present disclosure provide an image editing system for perform image object replacement or image region replacement (e.g., an image editing system for replacing an object or region of an image with an object or region from another image). For example, the image editing system may replace a sky portion of an image with a more desirable sky portion from a different replacement image. The original image and the replacement image (e.g., the image including a desirable object or region) include layers of masks. A sky from the replacement image may replace the sky of the image to produce an aesthetically pleasing composite image.

Sky replacement

Systems and methods for image editing are described. Embodiments of the present disclosure provide an image editing system for performing image object replacement or image region replacement (e.g., an image editing system for replacing an object or region of an image with an object or region from another image). For example, the image editing system may replace a sky portion of an image with a more desirable sky portion from a different replacement image. According to some embodiments described herein, thumbnails, region location information, and image metadata from multiple preset images can be stored together and loaded for presentation and selection of a preset image for replacing a region of an image. Once a preset image (e.g., an image with a replacement sky) is selected, a high-resolution version of the image can be loaded and used to generate a composite image.

Sky replacement preset loading

Methods and systems are provided for presenting and using multiple masks based on a segmented image in editing the image. In particular, multiple masks can be presented to a user using a graphical user interface for easy selection and utilization in the editing of an image. The graphical user interface can include a display configured to display an image, a mask zone configured to display segmentations of the image using masks, and an edit zone configured to display edits to the image. Upon receiving segmentation for the image, the masks can be displayed in the mask zone where the masks are based on a selected segmentation detail level.

Presenting multiple image segmentations

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

Systems and techniques for automatic object replacement in an image include receiving an original image and a preferred image. The original image is automatically segmented into an original image foreground region and an original image object region. The preferred image is automatically segmented into a preferred image foreground region and a preferred image object region. A composite image is automatically composed by replacing the original image object region with the preferred image object region such that the composite image includes the original image foreground region and the preferred image object region. An attribute of the composite image is automatically adjusted.

Automatic object replacement in an image

Embodiments of the present invention are directed at providing a font similarity system. In one embodiment, a new font is detected on a computing device. In response to the detection of the new font, a pre-computed font list is checked to determine whether the new font is included therein. The pre-computed font list including feature representations, generated independently of the computing device, for corresponding fonts. In response to a determination that the new font is absent from the pre-computed font list, a feature representation for the new font is generated. The generated feature representation capable of being utilized for a similarity analysis of the new font. The feature representation is then stored in a supplemental font list to enable identification of one or more fonts installed on the computing device that are similar to the new font. Other embodiments may be described and/or claimed.

Dynamic font similarity

Systems and techniques for identification of fonts include receiving a selection of an area of an image including text, where the selection is received from within an application. The selected area of the image is input to a font matching module within the application. The font matching module identifies one or more fonts similar to the text in the selected area using a convolutional neural network. The one or more fonts similar to the text are displayed within the application and the selection and use of the one or more fonts is enabled within the application.

Identification of fonts in an application

A digital medium environment is described to automatically generate a trimap and segment a digital image, independent of any user intervention. An image processing system receives an image and a low-resolution mask for the image, which provides a probability map indicating a likelihood that a pixel in the image mask corresponds to a foreground object in the image. The image processing system analyzes the image to identify content in the image's foreground and background portions, and adaptively generates a trimap for the image based on differences between the identified foreground and background content. By identifying content of the image prior to generating the trimap, the techniques described herein can be applied to a wide range of images, such as images where foreground content is visually similar to background content, and vice versa. Thus, the image processing system can automatically generate trimaps for images having diverse visual characteristics.

Automatic trimap generation and image segmentation

Embodiments of the present invention are directed at providing a font similarity preview for non-resident fonts. In one embodiment, a font is selected on a computing device. In response to the selection of the font, a pre-computed font list is checked to determine what fonts are similar to the selected font. In response to a determination that similar fonts are not local to the computing device, a non-resident font list is sent to a font vendor. The font vendor sends back previews of the non-resident fonts based on entitlement information of a user. Further, a full non-resident font can be synced to the computing device. Other embodiments may be described and/or claimed.

Non-resident font preview

The present disclosure relates to a font recognition system that employs a multi-task learning framework and training to improve font classification and remove negative side effects caused by intra-class variances of glyph content. For example, in one or more embodiments, the font recognition system trains a hybrid font recognition neural network that includes two or more font recognition neural networks and a weight prediction neural network. The hybrid font recognition neural network determines and generates classification weights based on which font recognition neural network within the hybrid font recognition neural network is best suited to classify the font in an input text image. By employing a hybrid trained font classification neural network, the font recognition system can improve overall font recognition as well as remove the negative side effects from diverse glyph content.

Font recognition by dynamically weighting multiple deep learning neural networks

Text region detection techniques and systems for digital images using image tag filtering are described. These techniques and systems support numerous advantages over conventional techniques through use of image tags to filter text region candidates. A computing device, for instance, may first generate text region candidates through use of a variety of different techniques, such as text line detection. The computing device then assigns image tags to the text region candidates. The assigned image tags are then used by the computing device to filter the text region candidates based on whether image tags assigned to respective candidates are indicative of text.

Text region detection in digital images using image tag filtering

The present disclosure is directed toward systems and methods for generating an interactive digital media item based on a two-dimensional 'selfie.' For example, one or more embodiments described herein identifies a face in the two-dimensional 'selfie,' then builds and displays a three-dimensional model based on the identified face. One or more embodiments described herein also track movement of a viewer of a computing device displaying the three-dimensional model such that one or more portions of the three-dimensional model appear to follow the person viewing the 'selfie.'

Growing community of inventors

Palo Alto, CA, United States of America

I-Ming Pao