Abstract: A method, system, and computer-readable storage medium for applying Gaussian Mixture Models (GMMs) to local image patches using an adaptive color lookup table. Per-channel color quantization may be performed to find representative colors for a local image patch. Each combination of the representative values corresponds to a representative color. The probabilities of the representative colors may be computed using a local GMM color model and stored to corresponding entries in an adaptive color lookup table. For every pixel in an image patch, the closest representative color may be found, and the corresponding probability may be retrieved from the lookup table and used for the pixel. The method may, for example, be applied to each local window in a method for automatically determining segmentation in a digital video image sequence to calculate the foreground probabilities for the pixels in a propagated classifier via a GMM.

Abstract: A sharp frame and a blurred frame are detected from among a plurality of frames. A blur kernel is estimated. The blur kernel represents a motion-transform between the sharp frame and the blurred frame. Using the blur kernel, a static region measure for the sharp frame and the blurred frame is estimated. A de-blurred frame is generated by replacing one or more pixels of the blurred frame as indicated by the static region measure.

Abstract: Systems, methods and apparatus, including computer program products, implementing and using techniques for generating a composite image from both two-dimensional (2D) image layers and three-dimensional (3D) image layers. In one embodiment, the image layers are arranged in a sequence. The image layers are rendered according to the sequence to generate a composite image, the last image layer of the sequence to be rendered being a 2D image layer.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for determining validity of cached frames of a compositing hierarchy as a composition tree of a digital video composition is edited. The techniques use interval lists associated with nodes in a compositing tree to determine which cached frames of a composition hierarchy are guaranteed to be valid in the face of arbitrary edits to the hierarchy.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for generating a composite image from both two-dimensional (2D) image layers and three-dimensional (3D) image layers. In one embodiment, the image layers are arranged in a sequence in which a top 3D image layer is separated from a bottom 3D image layer by a 2D image layer and the image layers are rendered according to the sequence. In another embodiment, at least one of the image layers is associated with an adjustment layer, and rendering the composite image includes determining whether each current image layer has an associated adjustment layer with a dimensionality different from that of the current image layer, and if it does, applying the adjustment layer accordingly. In another embodiment, at least one of the image layers is associated with a track matte.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for generating a composite image. Electronic data representing image layers to be combined in a composite image is provided. At least one of the image layers has two-dimensional content. At least one of the image layers has three-dimensional content. The layers are arranged in a composition sequence list. The image layers are grouped into metalayers including image layers with content of a common dimensionality. The metalayers are arranged in a metalayer sequence. A metalayer is selected according to the metalayer sequence and the image layers in the selected metalayer are processed to generate a raster representation of the image layers in the selected metalayer. The raster representation is composited into an image buffer and the process is repeated until the raster representation of each of the metalayers have been composited into the image buffer to form a composite image.

Abstract: A method of integrating two independent simulations including running a first simulation simulating changes in an object over time. The first simulation includes a first simulation output reflective of a state of the first simulation at one or more predefined times. A second simulation is run concurrently simulating changes in a second object over time. An interaction between the first and second simulations is defined resulting in an integrated simulation output without affecting the first simulation state.

Abstract: A computer-implemented method and apparatus for reparameterizing a parametric function representing an animation feature in an animation system where the parametric function is represented by a curve having unequal arc-length per unit parameter. The system samples at intervals of the parameter along the length of the curve and then calculates the arc-length over each interval. Thereafter, one or more differentiable curves are fitted to the parameter, arc-length pairs.

Abstract: A computer-implemented method for delaying the rendering of source material associated with a source layer in a nested composition that is a layer in a root composition. During the rendering of the root composition the method retrieves the source layer, promotes the source layer to the root layer and delays the rendering of the source material until the root layer is rendered.

Abstract: A computer-implemented method and apparatus for animating a property (such as the position of an object) using floating keyframes to selectively decouple property space and time constraints. Fixed keyframes and floating keyframes may used to specify a path through an n-dimensional property space, but the motion along the path is controlled only by the fixed keyframes. The timing of the floating keyframes is determined by temporal attributes of the nearest fixed keyframes.

Abstract: A computer-implemented method and apparatus for rendering a composition where the user selects a composition to be rendered, a set of render settings and two or more different output format definitions to create output of two or more different formats. The composition is rendered according to the user-selected render settings to create master frames. The master frames are transformed according to each output format definition to create formatted frames in the selected output format.

Abstract: A method for compositing first and second digital images having different pixel aspect ratios to reduce distortion of image content. The method includes determining a scaling factor from first and second pixel aspect ratios; scaling a first image by the scaling factor; and compositing the first and second images into a composite image. The scaling step may be limited to stretching or squashing the first image in only a horizontal direction. The scaling step may include resampling the first image. In another aspect, the invention features a method for controlling motion along a motion path in a composition having nonsquare pixels. The method includes determining a scaling factor based on the composition pixel aspect ratio; applying the scaling factor to a copy of the motion path; reparameterizing the copy of the motion path to generate a scaled motion mapping; and using the scaled motion mapping to control motion along the motion path. The motion path may define the motion of a layer in the composition.