-
公开(公告)号：US10672174B2
公开(公告)日：2020-06-02
申请号：US16022387
申请日：2018-06-28
Applicant: Adobe Inc.
Inventor： Mridul Kavidayal , Vineet Batra , Matthew David Fisher , Ankit Phogat
Abstract: Systems and techniques are described for determining image handle locations. An image is provided to a neural network as input, and the neural network translates the input image to an output image that includes clusters of pixels against a background that have intensities greater than an intensity of the background and that indicate candidate handle locations. Intensities of clusters of pixels in an output image are compared to a threshold intensity level to determine a set of the clusters of pixels satisfying an intensity constraint. The threshold intensity level can be user-selectable, so that a user can control a density of handles. A handle location for each cluster of the set of clusters is determined from a centroid of each cluster. Handle locations include a coordinate for the handle location and an attribute classifying a degree of freedom for a handle at the handle location.
-
Patent Agency Ranking
公开(公告)号：US10510186B2
公开(公告)日：2019-12-17
申请号：US15852924
申请日：2017-12-22
Applicant: Adobe Inc.
Inventor： Vineet Batra , Mridul Kavidayal , Matthew David Fisher , Daniel M. Kaufman , Ankit Phogat
Abstract: Techniques for intuitive modifications of digital graphics in a digital media environment are described. For example, a digital graphics creation system accesses vector artwork including a vector object, such as a Bezier curve. The digital graphics creation system receives user inputs, including a user input defining handles on the vector object and a user input interacting with the handles indicating a desired change to the vector object. The digital graphics creation system modifies the vector artwork, including the vector object, by accounting for topology of the vector object and maintaining connections between connected segments of the vector object. The digital graphics creation system outputs the modified vector artwork, including the vector object, such as in a user interface.
-
公开(公告)号：US10482577B2
公开(公告)日：2019-11-19
申请号：US15220834
申请日：2016-07-27
Applicant: Adobe Inc.
Inventor： Tarun Beri , Vineet Batra , Harish Kumar
Abstract: Dynamic spread anti-aliasing is described. In some embodiments, a filled object is segmented into control tiles. Along the object border, multiple exterior control tiles respectively correspond to multiple curves forming the border. For each curve, one side is filled and the other is anti-aliased to smooth the appearance of the filled object. Each exterior control tile is expanded to create an expanded control tile having a spread zone that includes additional pixels. For example, a control triangle is transformed into a control rectangle, and the control rectangle is enlarged to create an expanded control rectangle by extending an edge outward and away from the curve on the side to be anti-aliased. The additional pixels of the spread zone are subjected to anti-aliasing, such as by applying alpha modulation to the pixels based on respective distances between the pixels and the curve. For subpixel zoom levels, pixel color can be adjusted.
-
公开(公告)号：US10410317B1
公开(公告)日：2019-09-10
申请号：US15936299
申请日：2018-03-26
Applicant: Adobe Inc.
Inventor： Ankit Phogat , Vineet Batra
IPC: G06T3/00
Abstract: A digital image transformation environment is described that employs spline handles. A spline handle is generated by a spline handle generation module of the computing device based on a segment with respect to artwork in a digital image as including control points. A second user input is then received as moving an internal point on the spline handle between the first and second endpoints from a first location to a second location in the user interface. In response, the spline handle generation module regenerates the segment of the spline handle as including the internal point at the second location by adjusting a tangent handle. Next, a digital image transformation module is employed to determine a transformation to be applied to the artwork based on the regenerated segment of the spline handle, which is applied to the artwork.
-
公开(公告)号：US10388045B2
公开(公告)日：2019-08-20
申请号：US15861908
申请日：2018-01-04
Applicant: Adobe Inc.
Inventor： Vineet Batra , Matthew David Fisher , Kevin John Wampler , Daniel M. Kaufman , Ankit Phogat
Abstract: Systems and techniques are described herein for generating a triangle mesh for an image represented by curves (e.g., Bezier segments). An outline of an image is determined and reduced to a set of connected polylines that are efficiently represented in an edge list. A triangle mesh is generated based on the edge list, rather than by directly sampling the curves of the image and using the samples as vertices of triangles. Thus, the triangle mesh is generated with a number of triangles independent from a number of curves representing the image. Samples of the curves are bound to the triangle mesh by representing the samples with barycentric coordinates with respect to a triangle in the mesh. Hence, once a mesh is deformed, locations of the samples are determined from the barycentric coordinates and triangles in the deformed mesh, and used to reconstruct the curves of the deformed image.
-
公开(公告)号：US20190206100A1
公开(公告)日：2019-07-04
申请号：US15861908
申请日：2018-01-04
Applicant: Adobe Inc.
Inventor： Vineet Batra , Matthew David Fisher , Kevin John Wampler , Daniel M. Kaufman , Ankit Phogat
CPC classification number: G06T11/40 , G06T11/203 , G06T11/60
Abstract: Systems and techniques are described herein for generating a triangle mesh for an image represented by curves (e.g., Bezier segments). An outline of an image is determined and reduced to a set of connected polylines that are efficiently represented in an edge list. A triangle mesh is generated based on the edge list, rather than by directly sampling the curves of the image and using the samples as vertices of triangles. Thus, the triangle mesh is generated with a number of triangles independent from a number of curves representing the image. Samples of the curves are bound to the triangle mesh by representing the samples with barycentric coordinates with respect to a triangle in the mesh. Hence, once a mesh is deformed, locations of the samples are determined from the barycentric coordinates and triangles in the deformed mesh, and used to reconstruct the curves of the deformed image.
-
-
-
-
-
Search Results
106
records
(took 0.021 seconds)
