Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: Systems and methods for providing real-time media communication services to make use of a software application resident on a server that receives the media feeds of multiple sending participants, and generates a single composed media feed that includes media feeds of the sending participants and that sends the composed media feed to other computing services for manifold purposes like recording, re-broadcasting and/or re-transmission to remote computing devices of multiple real-time media communication participants. The composed media feed can include supplementary information in addition to the media feeds of live participants. This supplementary information is provided by means of API configurable programmatic code that is then executed and used as the software application resident on the server.

Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: Systems and methods for providing real-time media communication services to make use of a software application resident on a server that receives the media feeds of multiple sending participants, and generates a single composed media feed that includes media feeds of the sending participants and that sends the composed media feed to other computing services for manifold purposes like recording, re-broadcasting and/or re-transmission to remote computing devices of multiple real-time media communication participants. The composed media feed can include supplementary information in addition to the media feeds of live participants. This supplementary information is provided by means of API configurable programmatic code that is then executed and used as the software application resident on the server.

Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.

Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: Methods and apparatus are provided for deblocking filtering on non-local intra prediction. An apparatus includes an encoder for encoding picture data using non-local intra prediction. The encoder includes a deblocking filter configured for use with non-local intra prediction modes so as to deblock filter at least a portion of the picture data encoded using the non-local intra prediction.

Abstract: There are provided methods and apparatus for adaptive geometric partitioning for video encoding and decoding. An apparatus includes an encoder for encoding image data corresponding to pictures by adaptively partitioning at least portions of the pictures responsive to at least one parametric model. The at least one parametric model involves at least one of implicit and explicit formulation of at least one curve.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.

Abstract: There are provided methods and apparatus supporting a multi-pass video structure for slice data. An apparatus includes an encoder for encoding at least one syntax data element related to at least two partitions of at least a portion of a picture. The at least one syntax element is encoded within a multi-pass syntax structure. The at least one syntax element belongs to a given class of data. The encoder encodes the at least one syntax data element with respect to all partitions of at least the portion of the picture prior to encoding a next class of data, wherein later coded data classes, including the next class, have at least one of an explicit coding and an implicit coding of at least one of a casual dependency and a non-casual dependency with respect to earlier coded data classes coded earlier than the next class.

Abstract: Methods and apparatus are provided for video coding and decoding with reduced bit-depth update mode and reduced chroma sampling update mode. An apparatus includes an encoder for encoding at least a portion of a picture using at least one of a reduced bit-depth update mode and a reduced chroma sampling update mode that respectively reduces at least one of a bit-depth and a chroma sampling of a residue signal corresponding to the portion.

Abstract: A method for generating a model of a flat object from views taken by at least two calibrated cameras, which is capable of generating two-dimensional and volumetric representations of the object, where the representations can be a depth map, a volumetric representation or a mesh representation, method including the following basic steps: calibrating at least two cameras, calculating several 3D coordinates of at least three points belonging to the same plane of the flat object, calculating the equation of the plane of the flat object, selecting at least one region representing the surface of the flat object, in at least one view provided by at least one camera, and calculating the intersection between the selected region representing the surface of the object and the equation of the plane.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.

Abstract: Implementations may relate to various aspects of modifying, or using, a coded bitstream, or to recovering watermarking information from data. In one implementation, a coded bitstream is modified to allow for the application of a watermark to the coded bitstream without changing the coding of any other syntax elements in the bitstream. This is performed by identifying conditions necessary to change a coded syntax element without disrupting the interpretation of subsequent coded elements. The coded syntax element is replaced with another coded value if the modified value generates the same decoding variables as the original value would have generated. Particular implementations focus on syntax elements coded using entropy coding, including, for example, Context-based Adaptive Binary Arithmetic Coding (CABAC). Regardless of the type of coding or watermarking, various implementations may provide for recovering watermarking information.

Abstract: There are provided methods and apparatus for fast geometric mode decision in a video encoder. An apparatus includes an encoder for performing a non-exhaustive geometric mode decision using geometric model-based partitioning modes. The encoder skips a testing of the geometric model-based partitioning modes based on at least one of a correlation and a dependence between the geometric model-based partitioning modes and non-geometric partitioning modes.

Abstract: There are provided methods and apparatus for in-loop artifact filtering. An apparatus includes an encoder for encoding an image region. The encoder has at least two filters for successively performing in-loop filtering to respectively reduce at least a first and a second type of quantization artifact.