Abstract: A system and method for the color correction of an image using three-dimensional, geometrical information of the capture environment of the image includes determining geometrical properties of at least a portion of the image and modifying a look of at least the portion of the image by altering a value of at least one of the determined geometrical properties and using image formation theory. In one embodiment of the present invention, the geometrical properties of the image include at least one of light properties, surface color, reflectance properties, and scene geometry of the at least one portion of the image. In accordance with the present invention, the geometrical properties of the image are alternatively determined by using sensing devices, by inferring the geometrical properties from the image itself, or by user input.

Abstract: At least one particular method and apparatus provide an enhanced quality low resolution image extracted from a scalable high resolution bit stream in a DCP bit stream. In various implementations, an enhancement layer is used to produce the enhanced low resolution image. The enhancement layer may include, for example, spatial-domain or frequency-domain information to be used to enhance the typical low resolution image extracted from a DCP bit stream. One specific process includes encoding a digital image into an encoded image. The encoded image is capable of being processed to provide a higher resolution decoding of the digital image and to provide a lower resolution decoding of the digital image. The process further includes encoding additional information for enhancing the lower resolution decoding to provide an enhanced lower resolution image. A complimentary signal and decoding process are also provided, as well as structures for performing the processes.

Abstract: A system and method for recovering three-dimensional (3D) particle systems from two-dimensional (2D) images are provided. The system and method of the present invention provide for identifying a fuzzy object in a two-dimensional (2D) image; selecting a particle system from a plurality of predetermined particle systems, the selected particle system relating to a predefined fuzzy object; generating at least one particle of the selected particle system; simulating the at least one particle to update states of the at least one particle; rendering the selected particle system; comparing the rendered particle system to the identified fuzzy object in the 2D image; and storing the selected particle system if the comparison result is within an acceptable threshold, wherein the stored particle system represents the recovered geometry of the fuzzy object.

Abstract: A method and system for modeling light in time and space are provided. The method and system of the present disclosure collect light readings, e.g., on a motion picture set, at different positions and times to build a light model to be used for visual effects (VFX) compositing. The light model represents the light distribution across space and/or time for a predetermined physical space. Using the light model, the lighting can then be predicted or interpolated at intermediate or other positions and/or times for which no specific light readings were obtained. The light models can be used for rendering objects (e.g., natural or CG elements) in a scene as if they were in that space.

Abstract: A system and method for region classification of two-dimensional images for 2D-to-3D conversion of images to create stereoscopic images are provided. The system and method of the present disclosure provides for acquiring a two-dimensional image, identifying a region of the 2D image, extracting features from the region, classifying the extracted features of the region, selecting a conversion mode based on the classification of the identified region, converting the region into a 3D model based on the selected conversion mode, and creating a complementary image by projecting the 3D model onto an image plane different than an image plane of the 2D image. A learning component optimizes the classification parameters to achieve minimum classification error of the region using a set of training images and corresponding user annotations.

Abstract: A film record comprises a film strip representing a plurality of frames. At least one of the frames includes at least one region wherein the optical density of the region is representative of a symbol from a constellation of symbols.

Abstract: A system and method for recovering three-dimensional (3D) particle systems from two-dimensional (2D) images are provided. The system and method of the present invention provide for identifying a fuzzy object in a two-dimensional (2D) image; selecting a particle system from a plurality of predetermined particle systems, the selected particle system relating to a predefined fuzzy object; generating at least one particle of the selected particle system; simulating the at least one particle to update states of the at least one particle; rendering the selected particle system; comparing the rendered particle system to the identified fuzzy object in the 2D image; and storing the selected particle system if the comparison result is within an acceptable threshold, wherein the stored particle system represents the recovered geometry of the fuzzy object.

Abstract: At least one particular method and apparatus provide an enhanced quality low resolution image extracted from a scalable high resolution bit stream in a DCP bit stream. In various implementations, an enhancement layer is used to produce the enhanced low resolution image. The enhancement layer may include, for example, spatial-domain or frequency-domain information to be used to enhance the typical low resolution image extracted from a DCP bit stream. One specific process includes encoding a digital image into an encoded image. The encoded image is capable of being processed to provide a higher resolution decoding of the digital image and to provide a lower resolution decoding of the digital image. The process further includes encoding additional information for enhancing the lower resolution decoding to provide an enhanced lower resolution image. A complimentary signal and decoding process are also provided, as well as structures for performing the processes.

Abstract: A method and system for modeling light in time and space are provided. The method and system of the present disclosure collect light readings, e.g., on a motion picture set, at different positions and times to build a light model to be used for visual effects (VFX) compositing. The light model represents the light distribution across space and/or time for a predetermined physical space. Using the light model, the lighting can then be predicted or interpolated at intermediate or other positions and/or times for which no specific light readings were obtained. The light models can be used for rendering objects (e.g., natural or CG elements) in a scene as if they were in that space.

Abstract: A system and method is provided for model fitting and registration of objects for 2D-to-3D conversion of images to create stereoscopic images. The system and method of the present disclosure provides for acquiring at least one two-dimensional (2D) image, identifying at least one object of the at least one 2D image, selecting at least one 3D model from a plurality of predetermined 3D models, the selected 3D model relating to the identified at least one object, registering the selected 3D model to the identified at least one object, and creating a complementary image by projecting the selected 3D model onto an image plane different than the image plane of the at least one 2D image. The registering process can be implemented using geometric approaches or photometric approaches.

Abstract: A system and method for the color correction of an image using three-dimensional, geometrical information of the capture environment of the image includes determining geometrical properties of at least a portion of the image and modifying a look of at least the portion of the image by altering a value of at least one of the determined geometrical properties and using image formation theory. In one embodiment of the present invention, the geometrical properties of the image include at least one of light properties, surface color, reflectance properties, and scene geometry of the at least one portion of the image. In accordance with the present invention, the geometrical properties of the image are alternatively determined by using sensing devices, by inferring the geometrical properties from the image itself, or by user input.

Abstract: A film record comprises a film strip representing a plurality of frames. At least one of the frames includes at least one region wherein the optical density of the region is representative of a symbol from a constellation of symbols.

Abstract: A system for collecting metadata in association with recorded content includes equipment configured to record and process content in the workflow. Metadata collection devices include devices incorporated in the equipment and/or devices configured to externally access the system. The metadata collection devices are configured to collect metadata and associate the metadata with the content at any point and any time in the workflow. The collected metadata can then be used to automate, facilitate and improve content processing in any part of the workflow.

Abstract: An apparatus comprising a detector for detecting optical density levels recorded on a film, each optical density level representing a symbol from a constellation of symbols, wherein each symbol is associated with a plurality of bits of data; and a demapper, for receiving data responsive to the detected optical density levels, and for providing data associated therewith. A method for recovering data stored on film by detecting optical density levels recorded on the film; and recovering the data from the detected optical density levels by receiving data responsive to the detected optical density levels; and demapping said received data for providing the recovered data associated therewith; wherein each detected optical density level is associated with a symbol from a constellation of symbols for use in demapping the data, and wherein each symbol is associated with a plurality of bits of data.

Abstract: A method for archiving a motion picture film can include capturing in a digital format at least one reference image set corresponding to at least one image from the motion picture film. At least one reference image set can be created which includes an unprocessed image captured, in the digital format, from an original camera negative. The image set can also include a processed image, stored in said digital format, that is a modified version of the unprocessed image. Subsequently, the reference image set can be recorded on a reference film medium to form a key frame reel. The key frame reel can thereafter be used to create monochrome color separations.