-
公开(公告)号：US11158090B2
公开(公告)日：2021-10-26
申请号：US16692503
申请日：2019-11-22
Applicant: Adobe Inc.
Inventor： Tharun Mohandoss , Pulkit Gera , Oliver Wang , Kartik Sethi , Kalyan Sunkavalli , Elya Shechtman , Chetan Nanda
Abstract: This disclosure involves training generative adversarial networks to shot-match two unmatched images in a context-sensitive manner. For example, aspects of the present disclosure include accessing a trained generative adversarial network including a trained generator model and a trained discriminator model. A source image and a reference image may be inputted into the generator model to generate a modified source image. The modified source image and the reference image may be inputted into the discriminator model to determine a likelihood that the modified source image is color-matched with the reference image. The modified source image may be outputted as a shot-match with the reference image in response to determining, using the discriminator model, that the modified source image and the reference image are color-matched.
-
公开(公告)号：US20210160466A1
公开(公告)日：2021-05-27
申请号：US16696160
申请日：2019-11-26
Applicant: Adobe Inc.
Inventor： Pulkit Gera , Oliver Wang , Kalyan Krishna Sunkavalli , Elya Shechtman , Chetan Nanda
Abstract: Systems and techniques for automatic digital parameter adjustment are described that leverage insights learned from an image set to automatically predict parameter values for an input item of digital visual content. To do so, the automatic digital parameter adjustment techniques described herein captures visual and contextual features of digital visual content to determine balanced visual output in a range of visual scenes and settings. The visual and contextual features of digital visual content are used to train a parameter adjustment model through machine learning techniques that captures feature patterns and interactions. The parameter adjustment model exploits these feature interactions to determine visually pleasing parameter values for an input item of digital visual content. The predicted parameter values are output, allowing further adjustment to the parameter values.
-
公开(公告)号：US20200304754A1
公开(公告)日：2020-09-24
申请号：US16359876
申请日：2019-03-20
Applicant: ADOBE INC.
Inventor： Nicolas Huynh Thien , William Marino , Oliver Wang , Nico Alexander Becherer , Allison Breanne Walke
Abstract: Embodiments of the present invention are directed towards reframing videos from one aspect ratio to another aspect ratio while maintaining visibility of regions of interest. A set of regions of interest are determined in frames in a video with a first aspect ratio. The set of regions of interest can be used to estimate an initial camera path. An optimal camera path is determined by leveraging the identified regions of interest using the initial camera path. Sub crops with a second aspect ratio different from the first aspect ratio of the video are identified. The sub crops are placed as designated using the optimal camera path to generate a cropped video with the second aspect ratio.
-
公开(公告)号：US20200302251A1
公开(公告)日：2020-09-24
申请号：US16897068
申请日：2020-06-09
Applicant: Adobe Inc.
Inventor： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
Abstract: The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
公开(公告)号：US20200273493A1
公开(公告)日：2020-08-27
申请号：US16281903
申请日：2019-02-21
Applicant: Adobe Inc.
Inventor： Bernd Huber , Bryan Russell , Gautham Mysore , Hijung Valentina Shin , Oliver Wang
IPC: G11B27/036 , G11B27/11 , H04N9/87 , G06F3/0486 , G06F17/27 , G06F3/0482 , G06F16/74 , G06F16/732 , G06F16/738
Abstract: Certain embodiments involve transcript-based techniques for facilitating insertion of secondary video content into primary video content. For instance, a video editor presents a video editing interface having a primary video section displaying a primary video, a text-based navigation section having navigable portions of a primary video transcript, and a secondary video menu section displaying candidate secondary videos. In some embodiments, candidate secondary videos are obtained by using target terms detected in the transcript to query a remote data source for the candidate secondary videos. In embodiments involving video insertion, the video editor identifies a portion of the primary video corresponding to a portion of the transcript selected within the text-based navigation section. The video editor inserts a secondary video, which is selected from the candidate secondary videos based on an input received at the secondary video menu section, at the identified portion of the primary video.
-
Patent Agency Ranking
公开(公告)号：US10701303B2
公开(公告)日：2020-06-30
申请号：US15937349
申请日：2018-03-27
Applicant: Adobe Inc.
Inventor： Oliver Wang , Pedro Morgado , Timothy Langlois
Abstract: Certain embodiments involve generating and providing spatial audio using a predictive model. For example, a generates, using a predictive model, a visual representation of visual content provideable to a user device by encoding the visual content into the visual representation that indicates a visual element in the visual content. The system generates, using the predictive model, an audio representation of audio associated with the visual content by encoding the audio into the audio representation that indicates an audio element in the audio. The system also generates, using the predictive model, spatial audio based at least in part on the audio element and associating the spatial audio with the visual element. The system can also augment the visual content using the spatial audio by at least associating the spatial audio with the visual content.
-
公开(公告)号：US20190295227A1
公开(公告)日：2019-09-26
申请号：US15935994
申请日：2018-03-26
Applicant: Adobe Inc.
Inventor： Oliver Wang , Michal Lukac , Elya Shechtman , Mahyar Najibikohnehshahri
Abstract: Techniques for using deep learning to facilitate patch-based image inpainting are described. In an example, a computer system hosts a neural network trained to generate, from an image, code vectors including features learned by the neural network and descriptive of patches. The image is received and contains a region of interest (e.g., a hole missing content). The computer system inputs it to the network and, in response, receives the code vectors. Each code vector is associated with a pixel in the image. Rather than comparing RGB values between patches, the computer system compares the code vector of a pixel inside the region to code vectors of pixels outside the region to find the best match based on a feature similarity measure (e.g., a cosine similarity). The pixel value of the pixel inside the region is set based on the pixel value of the matched pixel outside this region.
-
公开(公告)号：US20190251401A1
公开(公告)日：2019-08-15
申请号：US15897910
申请日：2018-02-15
Applicant: Adobe Inc.
Inventor： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
Abstract: The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
公开(公告)号：US10204423B2
公开(公告)日：2019-02-12
申请号：US15430659
申请日：2017-02-13
Applicant: Adobe Inc.
Inventor： Vladimir Kim , Oliver Wang , Minhyuk Sung , Mehmet Ersin Yumer
Abstract: Disclosed are techniques for more accurately estimating the pose of a camera used to capture a three-dimensional scene. Accuracy is enhanced by leveraging three-dimensional object priors extracted from a large-scale three-dimensional shape database. This allows existing feature matching techniques to be augmented by generic three-dimensional object priors, thereby providing robust information about object orientations across multiple images or frames. More specifically, the three-dimensional object priors provide a unit that is easier and more reliably tracked between images than a single feature point. By adding object pose estimates across images, drift is reduced and the resulting visual odometry techniques are more robust and accurate. This eliminates the need for three-dimensional object templates that are specifically generated for the imaged object, training data obtained for a specific environment, and other tedious preprocessing steps. Entire object classes identified in a three-dimensional shape database can be used to train an object detector.
-
公开(公告)号：US11756210B2
公开(公告)日：2023-09-12
申请号：US16817100
申请日：2020-03-12
Applicant: Adobe Inc.
Inventor： Oliver Wang , Matthew Fisher , John Nelson , Geoffrey Oxholm , Elya Shechtman , Wenqi Xian
Abstract: Certain aspects involve video inpainting in which content is propagated from a user-provided reference frame to other video frames depicting a scene. For example, a computing system accesses a set of video frames with annotations identifying a target region to be modified. The computing system determines a motion of the target region's boundary across the set of video frames, and also interpolates pixel motion within the target region across the set of video frames. The computing system also inserts, responsive to user input, a reference frame into the set of video frames. The reference frame can include reference color data from a user-specified modification to the target region. The computing system can use the reference color data and the interpolated motion to update color data in the target region across set of video frames.
-
-
-
-
-
-
-
-
-
Search Results
85
records
(took 0.021 seconds)
