Disney Enterprises, Inc.

Robert M Neuman

Evan Goldberg

Tara Handy Turner

Joseph W Longson

Matthew F Schnittker

Lewis Nathaniel Siegel

Andrew Hendrickson

Brian Whited

Paul Newell

David Anthony Bossert

Brandon Bloch

Henry Allen Driskill

Dmitriy Pinskiy

Philip McNally

Philip Mcnally

Evan M Goldberg

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 present application includes a computer implemented method including at least two modes for analyzing a stereoscopic image corresponding to a two dimensional image. The method includes analyzing one or more layers of the two dimensional image to determine a depth pixel offset for every pixel in the two dimensional image and creating by the processing element a depth map, such as a gray scale map, by coloring every pixel a color shade based on the respective depth pixel offset for the pixel. The method further includes displaying on a display an output image corresponding to the stereoscopic image, receiving a first user selection corresponding a first depth pixel offset, determining a plurality of pixels of the output image corresponding to the first depth pixel offset, and applying a first identifier to the plurality of pixels on the output image corresponding to the first depth pixel offset. Additionally, in a first mode the output image displayed includes the first identifier and in a second mode the output image displayed includes the depth map and the first identifier.

Depth identification of pixels in one or more three dimensional images

Implementations of the present invention involve methods and systems for converting a 2-D multimedia image to a 3-D multimedia image by utilizing a plurality of layers of the 2-D image. The layers may comprise one or more portions of the 2-D image and may be digitized and stored in a computer-readable database. The layers may be reproduced as a corresponding left eye and right eye version of the layer, including a pixel offset corresponding to a desired 3-D effect for each layer of the image. The combined left eye layers and right eye layers may form the composite right eye and composite left eye images for a single 3-D multimedia image. Further, this process may be applied to each frame of a animated feature film to convert the film from 2-D to 3-D.

Method and system for utilizing pre-existing image layers of a two-dimensional image to create a stereoscopic image

A computer-based method for generating a stereoscopic image from a two dimensional (2D) image such as a 2D cell animation. An object is selected in the 2D image, such as an animated character, and is stored in memory as the base image. With an erosion engine, the selected object is eroded to generate a set of eroded versions of the base image corresponding to a number of erosion levels. Each erosion level image may be formed by eroding or removing a set of outer or edge pixels from the image on the prior level. The method continues with calculating a parallax shift value for each of the eroded versions of the base image. An alternate eye image is then generated by compositing the set of eroded versions along with the base image. The eroded versions are horizontally offset from the base image by the level-specific parallax shift values.

Medial axis decomposition of 2D objects to synthesize binocular depth

Techniques for creating 3-D movies allow improved control over camera positioning parameters and editing of depth in post-process to provide for a smoother variation in the viewer's convergence distance and a more pleasant viewing experience. A director can define reference parameters related to a desired viewing experience, and camera positioning parameters are derived therefrom. A depth script specifying piecewise continuous variations in reference parameters can be applied in post-process to generate 3-D shots, scenes, or movies. These techniques can be applied in both computer-generated and live-action 3-D movies.

Generation of three-dimensional movies with improved depth control

Implementations of the present invention involve methods and systems for converting a 2-D image to a stereoscopic 3-D image and displaying the depth of one or more pixels of the 3-D image through an output image of a user interface. The pixels of the output image display the perceived depth of the corresponding 3-D image such that the user may determine the relative depth of the pixels of the image. In addition, one or more x-offset values or z-axis positions may be individually selected such that any pixel of the output image that correspond to the selected values is indicated in the output image. By providing the user with a visualization tool to quickly determine the perceived position of any pixel of a stereoscopic image, the user may confirm the proper alignment of the objects of the image in relation to the image as a whole.

Apparatus and method for indicating depth of one or more pixels of a stereoscopic 3-D image comprised from a plurality of 2-D layers

A method for performing stereo composition using multiple camera pairs. The method includes positioning first and second pairs of virtual cameras for imaging an animated scene. The method includes, with the first and second pairs of the cameras, obtaining 3D data for each camera for the animated scene. Then, a blending region is selected by defining a first boundary surface for the first pair of the cameras and a second boundary surface, spaced a distance apart from the first boundary surface, for the second pair of the cameras, with the blending region being the space between the first and second boundary surfaces. The method includes, with a blending module or function, combining the 3D data from a number of consequent cameras. The blending module monotonically increases the stereoscopic disparity function in a viewing direction and combines the 3D data in a continuous manner, e.g., to insure C1 continuity.

Stereo composition based on multiple camera rigs

Implementations of the present invention involve methods and systems for creating depth and volume in a 2-D planar image to create an associated 3-D image by utilizing a plurality of layers of the 2-D image, where each layer comprises one or more portions of the 2-D image. Each layer may be reproduced into a corresponding left eye and right eye layers, with one or both layers including a pixel offset corresponding to a perceived depth. Further, a depth model may be created for one or more objects of the 2-D image to provide a template upon which the pixel offset for one or more pixels of the 2-D image may be adjusted to provide the 2-D image with a more nuanced 3-D effect. In this manner, the 2-D image may be converted to a corresponding 3-D image with a perceived depth.

Gradient modeling toolkit for sculpting stereoscopic depth models for converting 2-D images into stereoscopic 3-D images

Implementations of the present disclosure involve methods and systems for creating depth and volume in a 2-D image by utilizing a plurality of layers of the 2-D image, where each layer comprises one or more portions of the 2-D image. Each layer may be reproduced into a corresponding left eye and right eye layers that include a depth pixel offset corresponding to a perceived depth. Further, a volume effect may also be applied to one or more objects of the 2-D image by associating a volume pixel offset to one or more pixels of the image. Thus, any pixel of the 2-D image may have a depth pixel offset to provide a perceived depth as well as a volume pixel offset to provide a stereoscopic 3-D volume effect. In this manner, the 2-D image may be converted to a corresponding stereoscopic 3-D image with perceived depth and volume effects applied.

Method and system for creating depth and volume in a 2-D planar image

A method for generating stereoscopic images with retinal rivalry effects. The method includes retrieving primary eye images and alternate eye images from memory. These images are filmed from horizontally offset cameras but include the same content. The method continues with processing the alternate eye images to introduce retinal rivalry such as by including a set of frames that have differing content from a corresponding set of frames from the primary eye images. The differing content, for example, may include an object rendered for the alternate eye that was not rendered in the primary eye images. The method may further include editing the primary eye images by inserting a transition and then editing the alternate eye images to perform the transition (e.g., a dissolve or cut) at a temporally offset transition point such as several frames later to introduce frames that differ in content from one eye stream to the other.

Stereoscopic images generated by adding content to alternate eye images for retinal rivalry

Implementations of the present invention involve methods and systems for converting a 2-D image to a stereoscopic 3-D image by segmenting one or more portions of the 2-D image based on one or more pixel color ranges. Further, a matte may be created that takes the shape of the segmented region such that several stereoscopic effects may be applied to the segmented region. In addition, ink lines that are contained within the segmented region may be removed to further define the corresponding matte. Implementations of the present disclosure also include a interface that provides the above functionality to a user for ease of segmentation and region selection. By utilizing the segmentation process, a 2-D image may be converted to a corresponding stereoscopic 3-D image with a perceived depth. Further, this process may be applied to each image of an animated feature film to convert the film from 2-D to 3-D.

Growing community of inventors

Santa Clarita, CA, United States of America

Robert M Neuman