15 results about "Bokeh" patented technology

This disclosure provides systems, methods, and devices for image signal processing that support adjusting a Bokeh effect in image data. In a first aspect, a method of image processing includes receiving a first user input specifying a first depth of focus. A camera is configured with a first aperture size of a plurality of aperture sizes of the camera that is nearest a second aperture size that corresponds to the first depth of focus. The first aperture size is smaller than the second aperture size. Image data representing a scene is received that is captured with the first aperture size of the camera. First modified image data is determined by applying a first blur kernel to the image data. The first modified image data represents the scene at the depth of focus corresponding to the second aperture size. Other aspects and features are also claimed and described.

The invention relates to the technical field of computer vision, and discloses a variable aperture scatter rendering method and system. The method comprises the following steps: firstly, acquiring a full-focus input image, a depth map and a target aperture parameter; inputting the full-focus input image into a neural network of an encoder-bottleneck layer-decoder structure to extract features; inputting the depth map and the target aperture parameter to an adaptive routing prompt module to generate a prompt vector; in an encoder stage, performing differentiation processing on the features through adaptive spatial routing by using a prompt vector, and inhibiting inter-region interference in combination with a depth map-based layered sparse attention mechanism; in a bottleneck layer and decoder stage, channel modulation is carried out by using a prompt vector and jump connection features are fused, and image details are gradually recovered; and finally, fusing the output scatter-scene residual image with the full-focus input image to generate a target aperture scatter-scene image. According to the method, the controllability, the boundary naturalness and the detail fidelity of boarder rendering are effectively improved.

An electronic device and method are disclosed. An electronic device includes a memory and a processor that implements the method, the method including obtaining image data of an image, setting a region of interest and a background region in the image using depth information, both including one or more sub-regions, the method further includes determining respective bokeh characteristics of the one or more first sub-regions and the one or more second sub-regions based on the first characteristic criterion and the second characteristic criterion, respectively, and processing the image to apply a bokeh effect to the plurality of pixels based on the respective bokeh characteristics of the one or more first sub-regions and the one or more second sub-regions.

Provided may be a method for: acquiring a luminance map having a higher bit depth than an input image; determining a distance difference between a reference pixel in focus and the current pixel in the input image by using a depth map corresponding to the input image; determining the size of a geometric kernel corresponding to the current pixel by using the distance difference between the reference pixel and the current pixel; and generating and outputting a bokeh image corresponding to the input image by using the luminance differences between the current pixel and neighboring pixels in the geometric kernel having the determined size and luminance weights based on the luminance map.

According to one embodiment, an electronic device may include at least one processor and at least one camera. The at least one processor may acquire an image through the at least one camera. The at least one processor may generate a depth map including depth data corresponding to a plurality of objects. The at least one processor may receive a user input for identifying an object that will not be blurred from among the plurality of objects. The at least one processor may identify an improvement area on the basis of the object and the depth map corresponding to the user input. The at least one processor may identify a focus area on the basis of the object and the depth map corresponding to the user input. The at least one processor may generate an output image on the basis of a synthesis of the focus area and a portion of the image excluding the focus area.

The present application relates to a kind of video monitoring image quality enhancement methods under adverse weather conditions, comprising the following steps: construct the blur rendering model based on generative adversarial network, then train and verify model;Blur rendering model includes discriminator, residual dense network, feature fusion module and generator;Initial image input blur rendering model is first judged by discriminator whether real sample or generated image, then, initial image input residual dense network, feature information of input image is extracted step by step, foreground target feature is strengthened, obtain multiple feature maps, generate feature fusion map after the fusion of multiple feature maps, generator adds random noise to feature fusion map, output generated image;Image denoising restoration model based on Unet model is constructed, and model is trained and verified after;Generated image is input into image denoising restoration model, and clear restored image is output.The present application has the advantages that foreground target information can be enhanced, and the authenticity and accuracy of image recovery can be ensured.

The present application relates to the technical field of computer vision, and discloses a variable aperture bokeh rendering method and system. The method first acquires a full-focus input image, a depth map thereof and a target aperture parameter; extracts features of the full-focus input image by inputting the full-focus input image into a neural network of an encoder-bottleneck layer-decoder structure; inputs the depth map and the target aperture parameter into an adaptive routing prompt module to generate a prompt vector; in the encoder stage, the prompt vector is used to differentially process the features through adaptive spatial routing, and a layered sparse attention mechanism based on the depth map is combined to suppress inter-region interference; in the bottleneck layer and the decoder stage, the prompt vector is used for channel modulation and fusion of the jump connection features to gradually restore image details; and finally, the output bokeh residual image is fused with the full-focus input image to generate a target aperture bokeh image. The present application effectively improves the controllability, boundary naturalness and detail fidelity of bokeh rendering.

This application discloses an image generation method and apparatus, belonging to the field of artificial intelligence technology. An embodiment of the method includes: acquiring an original image; inputting the original image into a bokeh parameter prediction model to obtain a bokeh parameter map; performing bokeh processing on the original image based on the bokeh parameter map to generate an initial bokeh image; and inputting the initial bokeh image into a bokeh image generation model to obtain a target bokeh image.

A processor generates a depth map from two images, including high dynamic range (HDR) images. The processor receives one or more first images from a first image sensor, where the one or more first images have a first field of view (FOV) and a first resolution, and receives one or more second images from a second image sensor, where the one or more second images have a second FOV and a second resolution. The processor generates a first HDR image from the one or more first images, and performs tone alignment on the one or more second images based on the first HDR image to generate a second HDR image. The processor generates a depth map using the first HDR image and the second HDR image. The processor can use the depth map to apply a bokeh effect to the first HDR image.

The utility model discloses an optical lens, which comprises a first lens, a second lens, a third lens, a fourth lens, a diaphragm, a fifth lens and a sixth lens which are sequentially arranged from an object side to an image side along an optical axis direction, the third lens and the fourth lens are glued to form a doublet lens; the first lens is provided with a convex surface and a concave surface and is installed in the forward direction or the reverse direction. When the first lens is installed in the forward direction, the convex surface faces the object side, and the concave surface faces the image side. When the first lens is reversely installed, the convex surface faces the image side, and the concave surface faces the object side. According to the optical lens, the first lens provided with the convex surface and the concave surface is installed in the forward direction or the reverse direction, the diaphragm and the multiple lenses are combined for cooperative imaging, the optical lens can have at least two imaging effects, standard imaging performance is provided through forward installation, and the conventional photographing requirement is met; the light propagation path is changed through reverse installation, so that background blurring light spots are radially diffused, and a unique out-of-focus bursting effect is formed.

This disclosure provides systems, methods, and devices for image signal processing that support adjusting a Bokeh effect in image data. In a first aspect, a method of image processing includes receiving a first user input specifying a first depth of focus. A camera is configured with a first aperture size of a plurality of aperture sizes of the camera that is nearest a second aperture size that corresponds to the first depth of focus. The first aperture size is smaller than the second aperture size. Image data representing a scene is received that is captured with the first aperture size of the camera. First modified image data is determined by applying a first blur kernel to the image data. The first modified image data represents the scene at the depth of focus corresponding to the second aperture size. Other aspects and features are also claimed and described.

This electronic device may comprise: at least one camera; a display; a memory storing instructions; and at least one processor including processing circuitry. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to: while a preview image obtained through the at least one camera is displayed through the display, receive a user input for setting a value of a virtual aperture; obtain a preview bokeh image on the basis of providing the value of the virtual aperture and the preview image to a bokeh model; and display the preview bokeh image through the display.

An image processing apparatus applies, to an input image, image restoration processing for correcting bokeh caused by a characteristic of an imaging optical system used to capture the input image. The image processing apparatus may further add a predetermined effect to a high luminance portion satisfying a predetermined condition in the input image to which the image restoration processing has been applied. The image processing apparatus has capabilities both correcting bokeh caused by an aberration in an optical system while keeping bokeh as photographic expression.