Disney Enterprises, Inc.

Siemens Aktiengesellschaft

Eth Zurich (eidgenoessische Technische Hochschule Zurich)

Brian Whited

Tong Fang

Gozde Unal

Maryann Simmons

Alexander Sorkine Hornung

Robert Walker Sumner

Gioacchino Noris

Markus Gross

Gregory G Slabaugh

Stelian Coros

Robert M Neuman

Jaroslaw Rossignac

Lewis Nathaniel Siegel

Jarek Rossignac

Michael Kaschalk

Eric A Daniels

David Anthony Bossert

Patrick T Osborne

Daniel Sykora

Brandon Bloch

Kyle D Odermatt

Gregory Gibran Slabaugh

Ariel Shamir

Gene S Lee

David Suroviec

A method for creating multiple viewpoint images for an image frame. The method includes receiving by a processing element a left eye image and a right eye image, wherein the left eye image and right eye image comprise a stereoscopic image pair. Once the images are received, the method includes determining by the processing element a first viewing location corresponding to the left eye image and a second viewing location corresponding to the right eye image and determining by the processing element a plurality of new viewpoint locations using the first viewing location and the second viewpoint location.

Varying display content based on viewpoint

Parallax based monoscopic rendering

The disclosure provides an approach for progressively sculpting three-dimensional (3D) geometry. In one configuration, a sculpting application receives time-based sculpts and stores the sculpted changes from the original geometry, referred to herein as 'offsets,' in 'fixes' which include (time, offsets) pairs, with the offsets being defined in relation to a reference frame. Each fix may further be associated with a &#x201c;set&#x201d; which includes portions of the geometry that are managed together. The sculpting application automatically provides smooth transitions between sculpts by applying scatter-data interpolation to interpolate the offsets of successive fixes, thereby generating new offsets for frames in between user-provided fixes. Further, the user may modify an envelope curve for a set to scale offsets, including offsets in fixes and those automatically generated through interpolation. In addition, tools are disclosed herein that permit a user to manipulate offsets, as opposed to manipulating the geometry itself.

Method and system for progressively sculpting three-dimensional geometry

Techniques are disclosed for creating animated video frames which include both computer generated elements and hand drawn elements. For example, a software tool may allows an artist to draw line work (or supply other 2D image data) to composite with an animation frame rendered from a three dimensional (3D) graphical model of an object. The software tool may be configured to determine how to animate such 2D image data provided for one frame in order to appear in subsequent (or prior) frames in a manner consistent with changes in rendering the underlying 3D geometry.

Techniques for processing image data generated from three-dimensional graphic models

A method for editing content including at least one three-dimensional object. The method includes determining by a processing element one or more constraints, rendering by the processing element a shell defining an offset distance to the three-dimensional object corresponding to the one or more constraints, receiving a user input to a point related or connected to the three-dimensional object, and moving the point in a direction corresponding to the user input. In the method, the movement of the point is limited in at least one direction by the shell.

Contextual editing using variable offset surfaces

Techniques are presented for controlling the amount of temporal noise in certain animation sequences. Sketchy animation sequences are received in an input in a digital form and used to create an altered version of the same animation with temporal coherence enforced down to the stroke level, resulting in a reduction of the perceived noise. The amount of reduction is variable and can be controlled via a single parameter to achieve a desired artistic effect.

Temporal noise control for sketchy animation

A method is provided for sketch segmentation via smart scribbles, the results of which are especially suitable for interactive real-time graphics editing applications. A vector-based drawing may be segmented into labels based on input scribbles provided by a user. By organizing the labeling as an energy minimization problem, an approximate solution can be found using a sequence of binary graph cuts for an equivalent graph, providing an optimized implementation in a polynomial time suitable for real-time drawing applications. The energy function may include time, proximity, direction, and curvature between strokes as smoothness terms, and proximity, direction, and oriented curvature between strokes and scribbles as data terms. Additionally, the energy function may be modified to provide for user control over locality control, allowing the selection of appropriately sized labeling regions by scribble input speed or scribble input pressure. Once the drawing is labeled, a wide range of drawing applications are enabled.

Smart scribbles for sketch segmentation

Embodiments facilitate the production of a B-spline curve that approximates a set of N-dimensional (position, pressures, tilt, etc.) discrete input samples recorded by a digital input device. Iterative noise filtering and B-spline subdivision processes are performed within a dynamic window of recent samples. A vector representation is produced at interactive rates after each new sample is captured, thus producing results that are comparable to what the same artist would expect if drawing on paper.

Systems and methods for interactive vectorization

A tool for inbetweening is provided, wherein inbetween frames are at least partly computer generated by analyzing elements of key frames to identify strokes, determining corresponding stroke pairs, computing a continuous stroke motion for each stroke pair, defined by a carrier defined by endpoints of the two strokes and, for mutual endpoints, adjusting the continuous stroke motion of the meeting strokes such that the adjustment results in the continuous stroke motion coinciding at the mutual endpoint such that the mutual endpoint would follow the same path and deforming the stroke as it is moved by the stroke motion, wherein the deformation is a weighted combination of deformations, each reconstructed using shape descriptors that are interpolated from the shape descriptors of the corresponding samples on the key frames, wherein the shape descriptors are computed from neighboring sample points in the cyclic order of samples along the stroke.

Tight inbetweening

A method and system for segmenting tubular structures in 3D images is disclosed. User inputs identifying a first region on the image inside of a tubular structure and a second region of the image outside of the tubular structure are received. Based on this information, an ordered series of pearls are generated along the tubular structure. Pearls are spheres, each having a center location and a radius determined based on the center locations and radii of previous pearls and on local voxel intensities in the image. A continuous model of the tubular structure can be generated by interpolating the center locations and radii of the ordered series of pearls. The ordered series of pearls can be displayed and easily edited in response to user input, thus providing an efficient and flexible method for interactive segmentation of a potion of interest in a tubular structure.

Method and system for segmentation of tubular structures in 3D images

A method and system for segmenting tubular or stroke-like structures in 2D images is disclosed. Examples of such structures include, but are not limited to, blood vessels, bones, roads, rivers, electrical wirings, and brush-strokes. User inputs identifying a first region on the image inside of a tubular structure and a second region of the image outside of the tubular structure are received. Based on this information, an ordered series of pearls are generated along the tubular structure. Pearls are 2D disks, each having a center location and a radius determined based on local pixel intensities in the image. A continuous model of the tubular structure is generated by interpolating the center locations and radii of the ordered series of pearls.

Method and system for segmentation of tubular structures using pearl strings

A method of computing a continuous interpolation of a discrete set of three-dimensional (3D) balls, including generating an initial skin, wherein the initial skin is a surface comprised of splines and wherein the splines touch each ball along a circle that is tangent to the ball, solving a first differential equation to minimize the initial skin's surface area or solving a second differential equation to minimize a squared mean curvature of the initial skin's surface, wherein the result of solving the first or second differential equations is an updated skin; and repeating the steps of solving the first or second differential equations for the updated skin, and then, repeating the steps of solving the first or second differential equations for each subsequently updated skin until a desired skin is realized.

Growing community of inventors

Glendale, CA, United States of America

Brian Whited