Microsoft Technology Licensing, LLC

Patrick Perez

Michel Gangnet

Andrew Blake

Kentaro Toyama

Antonio Criminisi

Michael Kallay

Eric Joel Stollnitz

John Michael Lounsbery

Devon Lyn Strawn

Andrew Y Wu

An example-based filling system identifies appropriate filling material to replace a destination region in an image and fills the destination region using this material, thereby alleviating or minimizing the amount of manual editing required to fill a destination region in image. Tiles of image data are borrowed from the proximity of the destination region or some other source to generate new image data to fill in the region. Destination regions may be designated by user input (e.g., selection of an image region by a user) or by other means (e.g., specification of a color or feature to be replaced). In addition, the order in which the destination region is filled by example tiles may be configured to emphasize the continuity of linear structures and composite textures using a type of isophote-driven image-sampling process.

Image region filling by exemplar-based inpainting

A system and method for generating color gradients is provided. The system generates color gradients using techniques from geometric surface modeling. The system and method of the present invention allow designers to specify very complex gradients in a simple way. The system can employ, for example, a vector-based interpolation method and/or a pixel-based partial differential equation (PDE) interpolation methods to facilitate generation of the color gradients. In one example, input boundary curves and/or feature curves are approximated by line segments, which are then utilized to generate a triangulation approximating a smooth color gradient.

Color gradient paths

Systems and methods are provided for interactive construction of an object boundary by minimizing a sum of costs, including costs associated with inconsistency of the image data and costs associated with undesired curve shape properties. A particle filter optimization algorithm is implemented that incorporates a variable strength, intrinsic preference for boundary smoothness. The particle filter generates alternative sequences of random moves, constructed in parallel, to avoid becoming stuck in local minima. Approximate optimization algorithms are utilized, keeping computational burden low, freeing resources to analyze intrinsic costs associated with local curvature. In one embodiment, a user may construct a curve by launching a particle stream, and by choosing visually satisfactory locations on the stream from which to relaunch particles. The user can also provide other input, such as drop down dams to redirect the stream at T-junctions. Additionally, a facility is incorporated to break the smoothness constraint automatically at corners of the object boundary.

Methods and system for providing image object boundary definition by particle filtering

An example-based filling system identifies appropriate filling material to replace a destination region in an image and fills the destination region using this material, thereby alleviating or minimizing the amount of manual editing required to fill a destination region in image. Tiles of image data are borrowed from the proximity of the destination region or some other source to generate new image data to fill in the region. Destination regions may be designated by user input (e.g., selection of an image region by a user) or by other means (e.g., specification of a color or feature to be replaced).

Image region filling by example-based tiling

A blended result image is computed using guided interpolation to alter image data within a destination domain. The destination domain may be altered based on a guided interpolator that is either dependent or not dependent upon a source image. When blending a source region into a destination region of an image, guided interpolation eliminates or minimizes apparent seams between the inserted region and the rest of the image. A variety of interpolation guides may be used to yield different effects in the blended results image. Such interpolation guides may include without limitation an identity guide, a smooth guide, a filtering guide, a transparent guide, a masking guide, and a weighted average combination of various guides.

Growing community of inventors

Cambridge, United Kingdom

Patrick Perez