Abstract: Appearance driven automatic three-dimensional (3D) modeling enables optimization of a 3D model comprising the shape and appearance of a particular 3D scene or object. Triangle meshes and shading models may be jointly optimized to match the appearance of a reference 3D model based on reference images of the reference 3D model. Compared with the reference 3D model, the optimized 3D model is a lower resolution 3D model that can be rendered in less time. More specifically, the optimized 3D model may include fewer geometric primitives compared with the reference 3D model. In contrast with the conventional inverse rendering or analysis-by-synthesis modeling tools, the shape and appearance representations of the 3D model are automatically generated that, when rendered, match the reference images.

Abstract: A method, computer readable medium, and system are disclosed for training a neural network model. The method includes the step of selecting an input vector from a set of training data that includes input vectors and sparse target vectors, where each sparse target vector includes target data corresponding to a subset of samples within an output vector of the neural network model. The method also includes the steps of processing the input vector by the neural network model to produce output data for the samples within the output vector and adjusting parameter values of the neural network model to reduce differences between the output vector and the sparse target vector for the subset of the samples.

Abstract: Apparatuses, systems, and techniques to identify one or more layers of a three-dimensional graphical image to generate a two-dimensional representation. In at least one embodiment, one or more layers of a three-dimensional graphical image are identified to generate one or more two-dimensional representations.

Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.

Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: An apparatus and method are described for asynchronous texel shading. For example, one embodiment of a graphics processing apparatus comprises: a first shader to perform shading operations on a plurality of pixels in a first pass and to submit a request to shade texels; and a texel shader to responsively perform texel shading operations in response to the request from the first shader, the texel shader to write results to a procedural texture stored in a memory subsystem, the procedural texture to be read during a second pass by the first shader or another shader.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: The performance of a neural network is improved by applying quantization to data at various points in the network. In an embodiment, a neural network includes two paths. A quantization is applied to each path, such that when an output from each path is combined, further quantization is not required. In an embodiment, the neural network is an autoencoder that includes at least one skip connection. In an embodiment, the system determines a set of quantization parameters based on the characteristics of the data in the primary path and in the skip connection, such that both network paths produce output data in the same fixed point format. As a result, the data from both network paths can be combined without requiring an additional quantization.

Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

Abstract: A method, computer readable medium, and system are disclosed for training a neural network. The method includes the steps of selecting an input sample from a set of training data that includes input samples and noisy target samples, where the input samples and the noisy target samples each correspond to a latent, clean target sample. The input sample is processed by a neural network model to produce an output and a noisy target sample is selected from the set of training data, where the noisy target samples have a distribution relative to the latent, clean target sample. The method also includes adjusting parameter values of the neural network model to reduce differences between the output and the noisy target sample.

Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: An apparatus and method are described for asynchronous texel shading. For example, one embodiment of a graphics processing apparatus comprises: a first shader to perform shading operations on a plurality of pixels in a first pass and to submit a request to shade texels; and a texel shader to responsively perform texel shading operations in response to the request from the first shader, the texel shader to write results to a procedural texture stored in a memory subsystem, the procedural texture to be read during a second pass by the first shader or another shader.

Abstract: A method, computer readable medium, and system are disclosed for training a neural network. The method includes the steps of selecting an input sample from a set of training data that includes input samples and noisy target samples, where the input samples and the noisy target samples each correspond to a latent, clean target sample. The input sample is processed by a neural network model to produce an output and a noisy target sample is selected from the set of training data, where the noisy target samples have a distribution relative to the latent, clean target sample. The method also includes adjusting parameter values of the neural network model to reduce differences between the output and the noisy target sample.

Abstract: A method, computer readable medium, and system are disclosed for training a neural network model. The method includes the step of selecting an input vector from a set of training data that includes input vectors and sparse target vectors, where each sparse target vector includes target data corresponding to a subset of samples within an output vector of the neural network model. The method also includes the steps of processing the input vector by the neural network model to produce output data for the samples within the output vector and adjusting parameter values of the neural network model to reduce differences between the output vector and the sparse target vector for the subset of the samples.

Abstract: A method for improving performance of generation of digitally represented graphics. The method comprises: receiving a first representation of a base primitive; providing a set of instructions associated with vertex position determination; executing said retrieved set of instructions on said first representation of said base primitive using bounded arithmetic for providing a second representation of said base primitive, and subjecting said second representation of said base primitive to a culling process. A corresponding apparatus and computer program product are also presented.

Abstract: A graphics processing apparatus and method are described.

Abstract: A unified compression/decompression architecture is disclosed for reducing memory bandwidth requirements in 3D graphics processing applications. The techniques described erase several distinctions between a texture (compressed once, and decompressed many times), and buffers (compressed and decompressed repeatedly during rendering of an image). An exemplary method for processing graphics data according to one or more embodiments of the invention thus begins with the updating of one or more tiles of a first image array, which are then compressed, using a real-time buffer compression algorithm, to obtain compressed image array tiles. The compressed image array tiles are stored for subsequent use as a texture. During real-time rendering of a second image array, the compressed image array tiles are retrieved and decompressed using a decompression algorithm corresponding to the buffer compression algorithm.