-
公开(公告)号：US11651477B2
公开(公告)日：2023-05-16
申请号：US16988055
申请日：2020-08-07
Applicant: Adobe Inc.
Inventor： He Zhang , Seyed Morteza Safdarnejad , Yilin Wang , Zijun Wei , Jianming Zhang , Salil Tambe , Brian Price
CPC classification number: G06T5/004 , G06N3/08 , G06T3/4046 , G06T7/194 , G06T2207/20081 , G06T2207/20084 , G06T2207/20132
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.
-
公开(公告)号：US20230128792A1
公开(公告)日：2023-04-27
申请号：US17589114
申请日：2022-01-31
Applicant: Adobe Inc.
Inventor： Jason Wen Yong Kuen , Su Chen , Scott Cohen , Zhe Lin , Zijun Wei , Jianming Zhang
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates object masks for digital objects portrayed in digital images utilizing a detection-masking neural network pipeline. In particular, in one or more embodiments, the disclosed systems utilize detection heads of a neural network to detect digital objects portrayed within a digital image. In some cases, each detection head is associated with one or more digital object classes that are not associated with the other detection heads. Further, in some cases, the detection heads implement multi-scale synchronized batch normalization to normalize feature maps across various feature levels. The disclosed systems further utilize a masking head of the neural network to generate one or more object masks for the detected digital objects. In some cases, the disclosed systems utilize post-processing techniques to filter out low-quality masks.
-
43.发明授权公开(公告)号：US11593948B2
公开(公告)日：2023-02-28
申请号：US17177595
申请日：2021-02-17
Applicant: Adobe Inc.
Inventor： Qihang Yu , Jianming Zhang , He Zhang , Yilin Wang , Zhe Lin , Ning Xu
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.
-
公开(公告)号：US20220284613A1
公开(公告)日：2022-09-08
申请号：US17186436
申请日：2021-02-26
Applicant: Adobe Inc.
Inventor： Wei Yin , Jianming Zhang , Oliver Wang , Simon Niklaus , Mai Long , Su Chen
Abstract: This disclosure describes one or more implementations of a depth prediction system that generates accurate depth images from single input digital images. In one or more implementations, the depth prediction system enforces different sets of loss functions across mix-data sources to generate a multi-branch architecture depth prediction model. For instance, in one or more implementations, the depth prediction model utilizes different data sources having different granularities of ground truth depth data to robustly train a depth prediction model. Further, given the different ground truth depth data granularities from the different data sources, the depth prediction model enforces different combinations of loss functions including an image-level normalized regression loss function and/or a pair-wise normal loss among other loss functions.
-
公开(公告)号：US11380023B2
公开(公告)日：2022-07-05
申请号：US16823092
申请日：2020-03-18
Applicant: Adobe Inc.
Inventor： Xin Sun , Ruben Villegas , Manuel Lagunas Arto , Jimei Yang , Jianming Zhang
Abstract: Introduced here are techniques for relighting an image by automatically segmenting a human object in an image. The segmented image is input to an encoder that transforms it into a feature space. The feature space is concatenated with coefficients of a target illumination for the image and input to an albedo decoder and a light transport detector to predict an albedo map and a light transport matrix, respectively. In addition, the output of the encoder is concatenated with outputs of residual parts of each decoder and fed to a light coefficients block, which predicts coefficients of the illumination for the image. The light transport matrix and predicted illumination coefficients are multiplied to obtain a shading map that can sharpen details of the image. Scaling the resulting image by the albedo map to produce the relight image. The relight image can be refined to denoise the relight image.
-
Patent Agency Ranking
公开(公告)号：US11256918B2
公开(公告)日：2022-02-22
申请号：US16874114
申请日：2020-05-14
Applicant: Adobe Inc.
Inventor： Zhe Lin , Xiaohui Shen , Mingyang Ling , Jianming Zhang , Jason Wen Yong Kuen
Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.
-
公开(公告)号：US11222399B2
公开(公告)日：2022-01-11
申请号：US16384593
申请日：2019-04-15
Applicant: Adobe Inc.
Inventor： Zhe Lin , Radomir Mech , Xiaohui Shen , Brian L. Price , Jianming Zhang , Anant Gilra , Jen-Chan Jeff Chien
Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.
-
公开(公告)号：US11138776B2
公开(公告)日：2021-10-05
申请号：US16416123
申请日：2019-05-17
Applicant: ADOBE INC.
Inventor： Radomir Mech , Jose Ignacio Echevarria Vallespi , Jingwan Lu , Jianming Zhang , Jane Little E
Abstract: Various methods and systems are provided for image-management operations that includes generating adaptive image armatures based on an alignment between composition lines of a reference armature and a position of an object in an image. In operation, a reference armature for an image is accessed. The reference armature includes a plurality of composition lines that define a frame of reference for image composition. An alignment map is determined using the reference armature. The alignment map includes alignment information that indicates alignment between the composition lines of the reference armature and the position of the object in the image. Based on the alignment map, an adaptive image armature is determined. The adaptive image armature includes a subset of the composition lines of the reference armature. The adaptive image armature is displayed.
-
公开(公告)号：US11132762B2
公开(公告)日：2021-09-28
申请号：US16557058
申请日：2019-08-30
Applicant: ADOBE INC.
Inventor： Amish Kumar Bedi , Sanyam Jain , Jianming Zhang
Abstract: Systems and methods are described for dynamically fitting a digital image based on the saliency of the image and the aspect ratio of a frame are described. The systems and methods may provide for identifying an aspect ratio of the frame, selecting a salient region of the digital image based on the aspect ratio using a saliency prediction model, and fitting the digital image into the frame so that a boundary of the frame is aligned with a boundary of the salient region.
-
公开(公告)号：US20210248748A1
公开(公告)日：2021-08-12
申请号：US16789088
申请日：2020-02-12
Applicant: Adobe Inc.
Inventor： Kerem Can Turgutlu , Jayant Kumar , Jianming Zhang , Zhe Lin
Abstract: Techniques are disclosed for parsing a source image, to identify segments of one or more objects within the source image. The parsing is carried out by an image parsing pipeline that includes three distinct stages comprising three respectively neural network models. The source image can include one or more objects. A first neural network model of the pipeline identifies a section of the source image that includes the object comprising a plurality of segments. A second neural network model of the pipeline generates, from the section of the source image, a mask image, where the mask image identifys one or more segments of the object. A third neural network model of the pipeline further refines the identification of the segments in the mask image, to generate a parsed image. The parsed image identifies the segments of the object, by assigning corresponding unique labels to pixels of different segments of the object.
-
-
-
-
-
-
-
-
-
Search Results
180
records
(took 0.024 seconds)
