Abstract: A computer-implemented method for forming a dataset configured for learning a Convolutional Neural Network (CNN) architecture including an image feature extractor. It comprises providing pairs of images, each pair comprising a reference image and a respective denoised image. For each pair of images, the method provides the pair of images to a pre-trained CNN architecture similar to the one the formed dataset will be configured for. The method computes an error map representing a difference between a first normalized feature of the denoised image and a second normalized feature of the reference image, the first and second normalized features being the output of a same layer of the pre-trained CNN architecture and adds the respective denoised image and the error map to the dataset. This constitutes an improved solution with respect to forming a dataset for learning a CNN architecture to identify areas of degradation generated by a denoiser.

Abstract: A computer-implemented method of machine learning including learning a Convolutional Neural Network (CNN) architecture for estimating a degradation generated by a denoiser on a ray traced image. The method includes obtaining a dataset and learning the CNN architecture based on the obtained dataset. The learning including taking as input an image generated by the denoiser and a corresponding noisy image of the provided dataset and outputting an error map. This forms an improved solution with respect to estimating a degradation generated by a denoiser on a ray traced image.

Abstract: The disclosure notably relates to a computer-implemented method for retrieving a similar virtual material appearance from a database. The method comprises providing a database including virtual material appearances associated to an appearance signatures computed from values representing at least one of a structure, a reflection and a color of the associated virtual material appearance. The method further comprises providing a first appearance signature associated to a first virtual material appearance. The method further comprises identifying one or more virtual material appearances similar to the first virtual material appearance by comparing the first appearance signature with appearance signatures respectively associated to virtual material appearances in the database. The method improves retrieval of virtual material appearances.

Abstract: The disclosure notably relates to a computer-implemented method for retrieving a similar virtual material appearance from a database. The method comprises providing a database including virtual material appearances associated to an appearance signatures computed from values representing at least one of a structure, a reflection and a color of the associated virtual material appearance. The method further comprises providing a first appearance signature associated to a first virtual material appearance. The method further comprises identifying one or to more virtual material appearances similar to the first virtual material appearance by comparing the first appearance signature with appearance signatures respectively associated to virtual material appearances in the database. The method improves retrieval of virtual material appearances.

Abstract: Methods, systems and computer program code (software) products executable in a digital processor operable to generate a synthetic image include (1) selecting a rank-1 lattice in accordance with a maximized minimum distance function (max-min-dist lattice) corresponding to points in the synthetic image to be generated; (2) generating a data structure for efficient access of data stored in points of the rank-1 lattice, the data structure including the number n of lattice points, generator vector g, s basis vectors, and indices of the basis vectors, wherein the basis vectors are lattice points, and (3) generating, using the rank-1 lattice, digital output representative of a synthetic image, wherein the generating includes using the layout of rank-1 lattice points to represent textures of arbitrary dimension.

Abstract: Methods, systems, devices, and computer program code (software) products enable acceleration of ray tracing by using acceleration data structures with high arity to enable processing of nodes using streaming SIMD (Single Instruction, Multiple Data) instructions with reduced memory requirements.

Abstract: Methods, systems, devices, and computer program code (software) products enable acceleration of ray tracing by using acceleration data structures with high arity to enable processing of nodes using streaming SIMD (Single Instruction, Multiple Data) instructions with reduced memory requirements.

Abstract: Methods, systems, devices, and computer program code (software) products enable acceleration of ray tracing by using acceleration data structures with high arity to enable processing of nodes using streaming SIMD (Single Instruction, Multiple Data) instructions with reduced memory requirements.

Abstract: Methods, systems and computer program code (software) products executable in a digital processor operable to generate a synthetic image include (1) selecting a rank-1 lattice in accordance with a maximized minimum distance function (max-min-dist lattice) corresponding to points in the synthetic image to be generated, (2) generating a data structure for efficient access of data stored in points of the rank-1 lattice, the data structure including the number n of lattice points, generator vector g, s basis vectors, and indices of the basis vectors, wherein the basis vectors are lattice points, and (3) generating, using the rank-1 lattice, digital output representative of a synthetic image, wherein the generating includes using the layout of rank-1 lattice points to represent textures of arbitrary dimension.

Abstract: Methods, systems, devices, and computer program code (software) products enable acceleration of ray tracing by using acceleration data structures with high arity to enable processing of nodes using streaming SIMD (Single Instruction, Multiple Data) instructions with reduced memory requirements.