Abstract: In one respect, there is provided a system that may include a processor and a memory. The memory may be configured to store instructions that results in operations when executed by the processor. The operations may include: training a machine learning model by at least processing a training set with the machine learning model, the training set including at least one synthetic image that is generated by applying one or more modifications to a non-synthetic image; determining, based at least on a result of the processing of the mixed training set, that the machine learning model is unable to classify images having a specific modification; and training the machine learning model with additional training data that includes one or more additional synthetic images having the specific modification. Related methods and articles of manufacture are also disclosed.

Abstract: A mechanism is described for facilitating hybrid rendering of graphics images in computing environments. A method of embodiments, as described herein, includes detecting the video stream including two-dimensional (2D) images, where the video stream is processed through a graphics pipeline at a computing device. The method may further include performing hybrid combination of a luma (Y)-plane with chrominance (UV)-planes to directly generate a YUV texture, wherein the YUV texture is used to generate three-dimensional (3D) images corresponding to the 2D images.

Abstract: In one respect, there is provided a system that may include a processor and a memory. The memory may be configured to store instructions that results in operations when executed by the processor. The operations may include: training a machine learning model by at least processing a training set with the machine learning model, the training set including at least one synthetic image that is generated by applying one or more modifications to a non-synthetic image; determining, based at least on a result of the processing of the mixed training set, that the machine learning model is unable to classify images having a specific modification; and training the machine learning model with additional training data that includes one or more additional synthetic images having the specific modification.. Related methods and articles of manufacture are also disclosed.

Abstract: A mechanism is described for facilitating hybrid rendering of graphics images in computing environments. A method of embodiments, as described herein, includes detecting the video stream including two-dimensional (2D) images, where the video stream is processed through a graphics pipeline at a computing device. The method may further include performing hybrid combination of a luma (Y)-plane with chrominance (UV)-planes to directly generate a YUV texture, wherein the YUV texture is used to generate three-dimensional (3D) images corresponding to the 2D images.

Abstract: A method for deforming a plurality of shapes is described wherein each of the shapes comprises a set of parametric curves. The method comprises: providing a parametric surface, and forming a deformed shape for each of the shapes by performing a symbolic composition between the parametric surface and each parametric curve from the set of parametric curves comprising the shape being deformed. The parametric surface is defined by two parameters varying over a parametric domain, such that each of the parametric curves comprising the shapes lies in the parametric domain of the surface.

Abstract: A method for the computation of a subdivision surface from a base mesh of coarse faces which requires no dynamic allocations is performed as follows. First, a static data structure is allocated. The static data structure includes a hierarchy of data arrays, where each of the data arrays is for storing control mesh data for a single coarse face at a respective subdivision level. The size of each of the data arrays is determined by the respective subdivision level. A subdivision algorithm is then applied to each of the base mesh coarse faces in turn. During the subdivision of a single coarse face, the resulting data for each subdivision level is stored in the respective data array. The static data structure may store further data for each subdivision level respectively, such as a tag for each of the sub-faces at the given level. The subdivision may be applied adaptively, by applying level-of-detail control information at intermediate subdivision levels.

Abstract: A method for deforming a plurality of shapes is described wherein each of the shapes comprises a set of parametric curves. The method comprises: providing a parametric surface, and forming a deformed shape for each of the shapes by performing a symbolic composition between the parametric surface and each parametric curve from the set of parametric curves comprising the shape being deformed. The parametric surface is defined by two parameters varying over a parametric domain, such that each of the parametric curves comprising the shapes lies in the parametric domain of the surface.