Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image and obtaining one or more guide channels. For each of a plurality of local neighborhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. At least one of (i) the noisy image, (ii) the one or more guide channels, and (iii) the denoised image, are stored in a quantized low-bitdepth format.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image at a first resolution; obtaining one or more guide channels at the first resolution, and obtaining one or more corresponding guide channels at a second resolution. The second resolution may be the same resolution as, or a higher resolution than, the first resolution. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels (at the first resolution), and applying the calculated parameters to the one or more guide channels at the second resolution, to produce a denoised image at the second resolution.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image and obtaining one or more guide channels. For each of a plurality of local neighborhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. At least one of (i) the noisy image, (ii) the one or more guide channels, and (iii) the denoised image, are stored in a quantized low-bitdepth format.

Abstract: Techniques are described for processing data in a convolutional neural network (CNN) via fused operations within encoder and/or decoder blocks of a feature network to increase computational efficiency and reduce memory usage. Padding units are added to the input data for each convolutional operation within the encoder/decoder blocks. In certain embodiments, the feature network is coupled to a filter network, forming a combined U-Net architecture in which each of one or more decoder blocks of the feature network is coupled to a corresponding block of the filter network, enabling parallel processing of the output feature maps via the corresponding blocks of the filter network.

Abstract: Techniques are described for denoising an input image using a tiled convolutional neural network (CNN). Input image data is segmented into a plurality of input tiles, each of which is processed using a respective thread group. Each thread group employs a U-Net structure comprising encoding stages, decoding stages, and a bottleneck stage, to generate corresponding output tiles. A set of core pixels is extracted from each padded output tile and used to generate a denoised output image using the extracted core pixels.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image and obtaining one or more guide channels. For each of a plurality of local neighborhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. At least one of (i) the noisy image, (ii) the one or more guide channels, and (iii) the denoised image, are stored in a quantized low-bitdepth format.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image; and obtaining one or more guide channels. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. Tiling is used when calculating the parameters of the model.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image; and obtaining one or more guide channels. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. Tiling is used when calculating the parameters of the model.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image at a first resolution; obtaining one or more guide channels at the first resolution, and obtaining one or more corresponding guide channels at a second resolution. The second resolution may be the same resolution as, or a higher resolution than, the first resolution. For each of a plurality of local neighbourhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels (at the first resolution), and applying the calculated parameters to the one or more guide channels at the second resolution, to produce a denoised image at the second resolution.

Abstract: A method of rendering an image of a 3-D scene includes rendering a noisy image and obtaining one or more guide channels. For each of a plurality of local neighborhoods, the method comprises: calculating the parameters of a model that approximates the noisy image as a function of the one or more guide channels, and applying the calculated parameters to produce a denoised image. At least one of (i) the noisy image, (ii) the one or more guide channels, and (iii) the denoised image, are stored in a quantized low-bitdepth format.

Abstract: An electronic device is disclosed. The electronic device comprises a plurality of cameras and a processor, wherein the processor may be configured to obtain a plurality of images using the plurality of cameras, to check a location of a region of interest among regions of the plurality of images that will be mapped to a polyhedron using a first assignment method, to map the plurality of images to the polyhedron using a second assignment method if the location of the region of interest is included in assigned conditions, and to generate image data using the polyhedron to which the plurality of images are mapped.

Abstract: An electronic device is disclosed. The electronic device comprises a plurality of cameras and a processor, wherein the processor may be configured to obtain a plurality of images using the plurality of cameras, to check a location of a region of interest among regions of the plurality of images that will be mapped to a polyhedron using a first assignment method, to map the plurality of images to the polyhedron using a second assignment method if the location of the region of interest is included in assigned conditions, and to generate image data using the polyhedron to which the plurality of images are mapped.

Abstract: An electronic device is provided. The electronic device includes a memory, a camera module, and a processor electrically connected to the memory and the camera module. The processor is configured to determine a first exposure value based on a brightness of an external object, sequentially capture a plurality of images using a first exposure value, a second exposure value having an exposure value less than the first exposure value, the first exposure value, and a third exposure value having an exposure value greater than the first exposure value, when a specified condition is satisfied, select a set of continuous images from the plurality of images, and generate a composite image using the set of continuous images.

Abstract: An electronic device is provided. The electronic device includes a memory, a camera module, and a processor electrically connected to the memory and the camera module. The processor is configured to determine a first exposure value based on a brightness of an external object, sequentially capture a plurality of images using a first exposure value, a second exposure value having an exposure value less than the first exposure value, the first exposure value, and a third exposure value having an exposure value greater than the first exposure value, when a specified condition is satisfied, select a set of continuous images from the plurality of images, and generate a composite image using the set of continuous images.

Abstract: An electronic device, method and computer readable medium are disclosed herein. The electronic device may comprise memory, such as the computer readable medium. The memory may include program instructions executable to implement the method, including identifying, by a controller, load information of the electronic device including execution of an application, detecting screen display information based on the identified load information by the controller, and controlling a display of the electronic device to display an execution screen of the application on the based on the detected screen display information.

Abstract: An electronic device, method and computer readable medium are disclosed herein. The electronic device may comprise memory, such as the computer readable medium. The memory may include program instructions executable to implement the method, including identifying, by a controller, load information of the electronic device including execution of an application, detecting screen display information based on the identified load information by the controller, and controlling a display of the electronic device to display an execution screen of the application on the based on the detected screen display information.