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

A method for generating a stereoscopic frame comprising:

• extracting a layer from a two-dimensional frame by a processing element, the layer comprising a first portion and a second portion of the two-dimensional frame, wherein the first portion corresponds to a first object;
• obtaining from a storage medium a gradient model comprising a gray scale template having a plurality of gray scale values relative to each of the first portion and second portion, wherein the gradient model takes the form of a geometric shape corresponding to the first object, the gradient model selected by the processing element from a plurality of gradient models on the storage medium;
• altering by the processing element the shape of the gradient model to approximate a portion of the two-dimensional frame;
• generating a duplicate layer comprising a duplicate of the first image portion and a duplicate of the second image portion;
• and
• horizontally offsetting the first image portion relative to the duplicate of the first image portion a first amount based on a portion of the plurality of gray scale values and the second image portion relative to the duplicate of the second image a second amount, different from the first amount, based on a portion of the plurality of gray scale values;
• wherein the layer and the duplicate layer are displayed substantially contemporaneously for stereoscopic viewing of the image.

A system for generating stereoscopic images from a two-dimensional planar image, the system comprising:

• one or more computing devices coupled with a storage medium storing one or more two-dimensional frames;
• the storage medium further including a plurality of digital geometric depth models, each geometric depth model including stereoscopic depth attributes;
• wherein the one or more computing devices are configured to perform the operations of:
• retrieving a first two-dimensional digital image comprising a first plurality of pixel values corresponding to a first object;
• obtaining a first depth model from the plurality of digital geometric depth models, the first depth model comprising a plurality of stereoscopic depth attributes relative to each of the first plurality of pixel values, wherein the first depth model is selected by a processing element based on the shape of the first object;
• obtaining a second two-dimensional digital image comprising a second plurality of pixel values corresponding to the first plurality of pixel values;
• and
• horizontally displacing one or more of the second plurality of pixel values based upon the plurality of stereoscopic depth attributes.