公开(公告)号：US11977829B2

公开(公告)日：2024-05-07

申请号：US17362031

申请日：2021-06-29

Applicant: Adobe Inc.

Inventor： Zhifei Zhang ,  Zhaowen Wang ,  Hailin Jin ,  Matthew Fisher

IPC: G06F40/109 ,  G06N3/045 ,  G06T11/20

CPC classification number: G06F40/109 ,  G06N3/045 ,  G06T11/203

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating scalable and semantically editable font representations utilizing a machine learning approach. For example, the disclosed systems generate a font representation code from a glyph utilizing a particular neural network architecture. For example, the disclosed systems utilize a glyph appearance propagation model and perform an iterative process to generate a font representation code from an initial glyph. Additionally, using a glyph appearance propagation model, the disclosed systems automatically propagate the appearance of the initial glyph from the font representation code to generate additional glyphs corresponding to respective glyph labels. In some embodiments, the disclosed systems propagate edits or other changes in appearance of a glyph to other glyphs within a glyph set (e.g., to match the appearance of the edited glyph).

公开(公告)号：US11842140B2

公开(公告)日：2023-12-12

申请号：US17657542

申请日：2022-03-31

Applicant: Adobe Inc.

Inventor： Arushi Jain ,  Vijit Saxena ,  Praveen Kumar Dhanuka ,  Matthew Fisher

IPC: G06F40/109 ,  G06F40/166 ,  G06F40/126 ,  G06V30/414 ,  G06V30/40

CPC classification number: G06F40/109 ,  G06F40/126 ,  G06F40/166 ,  G06V30/414 ,  G06V30/43

Abstract: Techniques described herein take character glyphs as input and generate a text-on-a-path text object that includes the character glyphs arranged in a determined order along a path. For instance, a method described herein includes accessing character glyphs in input data. The method further includes determining an order for the character glyphs based on relative positions and orientations of the character glyphs in the input data. The method further includes generating a path for the character glyphs, based on the order, and associating the path with the character glyphs. Further, the method includes generating a text object that includes the set of character glyphs arranged in the order along the path.

公开(公告)号：US11810326B2

公开(公告)日：2023-11-07

申请号：US17387207

申请日：2021-07-28

Applicant: Adobe Inc.

Inventor： Jonathan Eisenmann ,  Wenqi Xian ,  Matthew Fisher ,  Geoffrey Oxholm ,  Elya Shechtman

IPC: G06T7/80 ,  G06T7/12 ,  G06T7/13

CPC classification number: G06T7/80 ,  G06T7/12 ,  G06T7/13 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a critical edge detection neural network and a geometric model to determine camera parameters from a single digital image. In particular, in one or more embodiments, the disclosed systems can train and utilize a critical edge detection neural network to generate a vanishing edge map indicating vanishing lines from the digital image. The system can then utilize the vanishing edge map to more accurately and efficiently determine camera parameters by applying a geometric model to the vanishing edge map. Further, the system can generate ground truth vanishing line data from a set of training digital images for training the critical edge detection neural network.

公开(公告)号：US20210295606A1

公开(公告)日：2021-09-23

申请号：US16822819

申请日：2020-03-18

Applicant: Adobe Inc.

Inventor： Vladimir Kim ,  Pierre-alain Langlois ,  Oliver Wang ,  Matthew Fisher ,  Bryan Russell

IPC: G06T19/20 ,  G06T9/00 ,  G06T17/20

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for reconstructing three-dimensional meshes from two-dimensional images of objects with automatic coordinate system alignment. For example, the disclosed system can generate feature vectors for a plurality of images having different views of an object. The disclosed system can process the feature vectors to generate coordinate-aligned feature vectors aligned with a coordinate system associated with an image. The disclosed system can generate a combined feature vector from the feature vectors aligned to the coordinate system. Additionally, the disclosed system can then generate a three-dimensional mesh representing the object from the combined feature vector.

公开(公告)号：US11094083B2

公开(公告)日：2021-08-17

申请号：US16257495

申请日：2019-01-25

Applicant: Adobe Inc.

Inventor： Jonathan Eisenmann ,  Wenqi Xian ,  Matthew Fisher ,  Geoffrey Oxholm ,  Elya Shechtman

IPC: G06T7/80 ,  G06T7/12 ,  G06T7/13

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a critical edge detection neural network and a geometric model to determine camera parameters from a single digital image. In particular, in one or more embodiments, the disclosed systems can train and utilize a critical edge detection neural network to generate a vanishing edge map indicating vanishing lines from the digital image. The system can then utilize the vanishing edge map to more accurately and efficiently determine camera parameters by applying a geometric model to the vanishing edge map. Further, the system can generate ground truth vanishing line data from a set of training digital images for training the critical edge detection neural network.

公开(公告)号：US20210133477A1

公开(公告)日：2021-05-06

申请号：US16675529

申请日：2019-11-06

Applicant: Adobe Inc.

Inventor： Praveen Kumar Dhanuka ,  Matthew Fisher ,  Arushi Jain

IPC: G06K9/46 ,  G06F16/56 ,  G06F16/901

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining a glyph and a font from a vector outline by applying various combinations of hash-based querying, path-descriptor matching, or anchor-point matching. For example, the disclosed systems can select a subset of candidate glyphs for a vector outline based on (i) comparing hash keys of candidate glyphs with a point-order-agnostic hash key corresponding to the vector outline and (ii) comparing a path descriptor for a primary path of the vector outline to path descriptors corresponding to candidate glyphs. By further comparing anchor points between the vector outline and the subset of candidate glyphs, the disclosed systems can select both a glyph and a font matching the vector outline.

公开(公告)号：US10970458B1

公开(公告)日：2021-04-06

申请号：US16911569

申请日：2020-06-25

Applicant: Adobe Inc.

Inventor： Praveen Kumar Dhanuka ,  Matthew Fisher ,  Arushi Jain

IPC: G06F40/103 ,  G06F40/253

Abstract: Techniques are disclosed for clustering text. The techniques may be employed to cluster text blocks that are received in either sequential reading order or arbitrary order. A methodology implementing the techniques according to an embodiment includes receiving text blocks comprising elements that may include one or more of glyphs, characters, and/or words. The method further includes determining an order of the received text blocks as one of arbitrary order or sequential reading order. Text blocks received in sequential reading order progress from left to right and from top to bottom for horizontal oriented text, and from top to bottom and left to right for vertical oriented text. The method further includes performing z-order text clustering in response to determining that the received text blocks are in sequential reading order and performing sorted order text clustering in response to determining that the received text blocks are not in sequential reading order.

公开(公告)号：US10937237B1

公开(公告)日：2021-03-02

申请号：US16816080

申请日：2020-03-11

Applicant: Adobe Inc.

Inventor： Vladimir Kim ,  Pierre-alain Langlois ,  Matthew Fisher ,  Bryan Russell ,  Oliver Wang

IPC: G06T17/20 ,  G06T7/73 ,  G06T7/77 ,  G06T19/20 ,  G06N3/04

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for reconstructing three-dimensional object meshes from two-dimensional images of objects using multi-view cycle projection. For example, the disclosed system can determine a multi-view cycle projection loss across a plurality of images of an object via an estimated three-dimensional object mesh of the object. For example, the disclosed system uses a pixel mapping neural network to project a sampled pixel location across a plurality of images of an object and via a three-dimensional mesh representing the object. The disclosed system determines a multi-view cycle consistency loss based on a difference between the sampled pixel location and a cycle projection of the sampled pixel location and uses the loss to update the pixel mapping neural network, a latent vector representing the object, or a shape generation neural network that uses the latent vector to generate the object mesh.

公开(公告)号：US10748316B2

公开(公告)日：2020-08-18

申请号：US16159181

申请日：2018-10-12

Applicant: Adobe Inc.

Inventor： Ankit Phogat ,  Vineet Batra ,  Mridul Kavidayal ,  Matthew Fisher

IPC: G06T11/60 ,  G06F3/0484 ,  G06F17/16

Abstract: A selection of a key path of a vector image displayed using a graphical user interface (GUI) may be received, via the GUI. At least one candidate path of the vector image is identified. A pairwise comparison of the key path with the at least one candidate path is executed, the pairwise comparison including characterization of a translation, scaling, and rotation of the at least one candidate path with respect to the key path. Based on the pairwise comparison, it is determined that the at least one candidate path is within a similarity threshold defined with respect to the key path. A visual indicator of the at least one candidate path within the GUI, identifying the at least one candidate path as being within the similarity threshold, may be provided.

公开(公告)号：US20200242804A1

公开(公告)日：2020-07-30

申请号：US16257495

申请日：2019-01-25

Applicant: Adobe Inc.

Inventor： Jonathan Eisenmann ,  Wenqi Xian ,  Matthew Fisher ,  Geoffrey Oxholm ,  Elya Shechtman

IPC: G06T7/80 ,  G06T7/13 ,  G06T7/12

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a critical edge detection neural network and a geometric model to determine camera parameters from a single digital image. In particular, in one or more embodiments, the disclosed systems can train and utilize a critical edge detection neural network to generate a vanishing edge map indicating vanishing lines from the digital image. The system can then utilize the vanishing edge map to more accurately and efficiently determine camera parameters by applying a geometric model to the vanishing edge map. Further, the system can generate ground truth vanishing line data from a set of training digital images for training the critical edge detection neural network.