Abstract: Devices, systems and methods for generating high dynamic range images and video from a set of low dynamic range images and video using convolution neural networks (CNNs) are described. One exemplary method for generating high dynamic range visual media includes generating, using a first CNN to merge a first set of images having a first dynamic range, a final image having a second dynamic range that is greater than the first dynamic range. Another exemplary method for generating training data includes generating sets of static and dynamic images having a first dynamic range, generating, based on a weighted sum of the set of static images, a set of ground truth images having a second dynamic range greater than the first dynamic range, and replacing at least one of the set of dynamic images with an image from the set of static images to generate a set of training images.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: Devices, systems and methods for generating high dynamic range images and video from a set of low dynamic range images and video using convolution neural networks (CNNs) are described. One exemplary method for generating high dynamic range visual media includes generating, using a first CNN to merge a first set of images having a first dynamic range, a final image having a second dynamic range that is greater than the first dynamic range. Another exemplary method for generating training data includes generating sets of static and dynamic images having a first dynamic range, generating, based on a weighted sum of the set of static images, a set of ground truth images having a second dynamic range greater than the first dynamic range, and replacing at least one of the set of dynamic images with an image from the set of static images to generate a set of training images.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: Variable patch shape synthesis techniques are described. In one or more implementations, a plurality of patches are computed from one or more images, at least one of the plurality of patches having a different shape than another one of the plurality of patches. The shapes define an area to be considered for use in a patch synthesis technique. The patch synthesis technique is performed to edit an image using the computed plurality of patches having the different shapes.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: A method of producing noise-free images is disclosed. The method includes using machine learning incorporating a filter to output filter parameters using the training images. The machine learning may include training a neural network. The filter parameters are applied to Monte Carlo rendered training images that have noise to generate noise-free images. The training may include determining, computing and extracting features of the training images; computing filter parameters; applying an error metric; and applying backpropgation. The neural network may be a multilayer perceptron. The machine learning model is applied to new noisy Monte Carlo rendered images to create noise-free images. This may include applying the filter to the noisy Monte Carlo rendered images using the filter parameters to create the noise-free images.

Abstract: Variable patch shape synthesis techniques are described. In one or more implementations, a plurality of patches are computed from one or more images, at least one of the plurality of patches having a different shape than another one of the plurality of patches. The shapes define an area to be considered for use in a patch synthesis technique. The patch synthesis technique is performed to edit an image using the computed plurality of patches having the different shapes.