Adobe, Inc.

Ashlar, Inc.

Martin E Newell

Gregg Darryl Wilensky

Lubomir D Bourdev

Stephen N Schiller

Scott David Cohen

Daniel T Fitzpatrick

Hailin Jin

John W Peterson

Mark Andrew Ruzon

Peter Frank Ullmann

Niraj Gupta

Lubomir D Bourdey

Systems, methods, and apparatus, including computer program products, are provided for forming composite images. In some implementations, a method is provided. The method includes receiving a set of component images for forming a composite image and defining a first projection for the set of component images corresponding to a first reference frame. The method also includes identifying a plane corresponding to a point of view of the set of component images, where a normal to the plane corresponds to a second reference frame, defining a second projection for the set of component images corresponding to the second reference frame, the second reference frame corresponding to a rotation from the first reference frame defined using the normal of the identified plane, and rendering the composite image according to the second projection.

Panoramic image straightening

Methods, systems and apparatus, including computer program products, for processing a computer graphics illustration having pieces of artwork.

Processing illustration artwork

A digital image that includes first and second regions is processed. An intrinsic color of a given pixel located in an area of interest that is adjacent to at least one of the first and second regions is estimated by extrapolating from colors of multiple pixels in one of the first and second regions and multiple pixels in the other of the two regions.

Identifying intrinsic pixel colors in a region of uncertain pixels

Methods and systems, including computer program products, for determining a plurality of color clusters based on a plurality of pixels associated with a color image, the clusters being fewer than the pixels. A grayscale value for each one of a plurality of points in a color space is determined. Each grayscale value is based on a weighted average of target differences between each point and the clusters. Each of the pixels is associated with one or more of the points. A grayscale value for each pixel is identified based on the grayscale value of the associated one or more points.

Fast, adaptive color to grayscale conversion

One embodiment of the present invention provides a system that determines a background image for a sequence of image frames. During operation, the system receives a sequence of input image-frames, wherein an input image-frame associates pixels with pixel-attributes. The system then computes a labeling, wherein the labeling associates pixels in the output background image with input image-frames in the sequence of input image-frames. Next, the system determines the output background image using the sequence of input image-frames and the labeling.

Method and apparatus for determining the background of an image sequence

Methods, systems, and apparatus, including computer program products, for calculating or applying a gradient over a region in a multi-dimensional space. A boundary defines the shape of the region. A gradient specifies a value transition between a starting position and an ending position. The following actions are performed to calculate a gradient value at any point in the selected region: determining an interpolation vector extending from an effective origin included in the starting position through the point to the ending position and defining a gradient value for the point according to the gradient and based on the position of the point along the interpolation vector relative to the effective origin and an intersection point where the interpolation vector meets the boundary.

Methods and apparatus for generating shaped gradients

Computer programs and computer-implemented methods implement techniques for creating and manipulating related vector objects in an image. These include creating a first vector object or elements in an image, creating a second vector object or elements in the image, and in response to creating the second vector object(s) in the image, calculating one or more new values for a first attribute of the one or more attributes for the first vector object(s) based at least in part on one or more of the current attribute values for the second vector object(s). Relationships are defined between vector objects using equations that define a value (or values) for an attribute for one vector object or elements as a function of attribute value(s) defined for the same or different vector objects in the image. In preferred embodiments, the function includes equations defining an attractive force and a repulsive force between the attribute value(s).

Creating and manipulating related vector objects in an image

Computer programs and computer-implemented methods implement techniques for applying a modification operation to vector objects in an image. These include receiving user input applying a modification operation in an image, identifying one or more vector objects to be affected by the modification operation and changing one or more attribute values for one or more of the attributes of each identified vector object according to the modification operation. The techniques can also include receiving user input selecting one of a plurality of image processing modes, each of the image processing modes defining a method of changing attribute values for of one or more of the attributes. In preferred embodiments, feedback is provided to the user of how attribute values for the attributes of vector objects are changing within the image.

Modifying vector objects

In a shape manipulation method, relocation information is received indicative of an intended change in position of a target location on a Bezier shape, the contour of the Bezier shape being governed by control points. In response to the relocation information, new positions are determined for canonical locations on the shape based on predefined intended behaviors of the canonical locations.

Manipulation of curves and surfaces

Methods and computer programs for processing a computer graphics illustration having overlapping pieces of artwork. The method includes flattening at least some of the pieces of artwork into non-overlapping regions, storing information describing how the appearances of one or more pieces of artwork can be combined to determine an appearance for at least one of the non-overlapping regions, determining an appearance for at least one of the non-overlapping regions based on the stored information, and outputting the determined appearance.

A computer-implemented method modifies a curve in response to a user action through a graphical user interface in the computer system, with the curve being defined by control points. Each of the control points is identified in response to user input as a fixed control point, a selected control point, or a free control point. A displacement of selected points is received, and a free slope control point of the curve is mapped to a point Tp on a line t. An interpolation curve IC(t) is defined on the line t, and a point Tp is projected to the value of the interpolation curve IC(t) at t equals Tp to find a scale factor. The scale factor is multiplied by the displacement of the selected points to determine the displacement of the free control point. A computer-implemented graphical user interface method creates a Bezier curve segment on a display in a computer system. A selection of a first segment end point is received through a graphical user interface in the computer system. The position of a cursor on the computer display is received as a second segment end point. The first and second slope points are calculated so that the Bezier segment defined by the first and second segment end points and the first and second slope points approximates an arc. The calculated Bezier curve segment is displayed on the computer display.

Growing community of inventors

San Jose, CA, United States of America

Martin E Newell