A dual mode camera may have a camera module and a light source. The camera module may include a quasi-bandpass filter for passing visible light and passing an attenuated portion of near-infrared light to an image sensor for detection. A processor may determine an ambient lighting condition corresponding with an amount of ambient visible light detected by a photodetector. In response to a first ambient lighting condition, the processor may send a first control signal to an encoder to encode image data in monochrome, and another signal to activate a light source. In response to a second ambient lighting condition, the processor may send a second control signal to the encoder to encode image data in color. The light source may emit a band of near-infrared light corresponding with an atmospheric absorption band. The quasi-bandpass filter may attenuate a portion of near-infrared light corresponding with the same atmospheric absorption band.

In an image processing apparatus, an image corrector ascertains, for each pixel of a selected pixel region included in an image captured by an imaging unit, luminance-value ratios of respective colors of color filters in accordance with (i) a color luminance value of the corresponding pixel of the selected pixel region, and (ii) ascertainment data items predetermined for the respective colors if a measured illumination level around the imaging unit is lower than or equal to a predetermined threshold illumination level. The ascertainment data item, predetermined for each color, represents a corresponding color luminance-value ratio at any pixel in the selected pixel region with respect to a predetermined peak luminance value of the corresponding color in the selected pixel region. The image corrector generates a corrected image in accordance with the luminance-value ratios of the respective colors ascertained for each pixel of the selected pixel region.

The present disclosure discloses a method for generating texture maps through multi-angle lighting photographing, comprising: constructing a multi-angle lighting photographing environment; photographing color chart images for color correction matrix; photographing white paper images for light intensity correction coefficient; capturing calibration images for transparency calculation; photographing object images for color correction and light intensity correction, including images without backlighting and images with backlighting; generating base color maps, normal maps, metallic maps, roughness maps, and transparency maps. The present disclosure also discloses a storage medium, wherein a computer program is stored, and the computer program is configured to be executed at runtime to perform the above-mentioned method. The present disclosure further discloses an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned method.

The present disclosure discloses a method for generating texture maps through multi-angle lighting photographing, comprising: constructing a multi-angle lighting photographing environment; photographing color chart images for color correction matrix; photographing white paper images for light intensity correction coefficient; capturing calibration images for transparency calculation; photographing object images for color correction and light intensity correction, including images without backlighting and images with backlighting; generating base color maps, normal maps, metallic maps, roughness maps, and transparency maps. The present disclosure also discloses a storage medium, wherein a computer program is stored, and the computer program is configured to be executed at runtime to perform the above-mentioned method. The present disclosure further discloses an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned method.

Disclosed is an image sensing device and an operating method thereof. The image sensing device may include an analyzer suitable for analyzing a state of each of multiple kernels based on system information and a plurality of pixel values, a detector suitable for detecting color noise of a target pixel value among pixel values included in a target kernel among the multiple kernels, according to the analysis result of the analyzer, and a corrector suitable for correcting the target pixel value according to the detection result of the detector.

In some implementations, a method of synchronizing a content generation and delivery architecture to reduce the latency associated with image passthrough. The method includes: determining a temporal offset associated with the content generation and delivery architecture to reduce a photon-to-photon latency across the content generation and delivery architecture; obtaining a first reference rate associated with a portion of the content generation and delivery architecture; generating, via synchronization circuitry, a synchronization signal for the content generation and delivery architecture based at least in part on the first reference rate; and operating the content generation and delivery architecture according to the synchronization signal and the temporal offset.

In some implementations, a method of synchronizing a content generation and delivery architecture to reduce the latency associated with image passthrough. The method includes: determining a temporal offset associated with the content generation and delivery architecture to reduce a photon-to-photon latency across the content generation and delivery architecture; obtaining a first reference rate associated with a portion of the content generation and delivery architecture; generating, via synchronization circuitry, a synchronization signal for the content generation and delivery architecture based at least in part on the first reference rate; and operating the content generation and delivery architecture according to the synchronization signal and the temporal offset.

A method for color restoration in images includes accessing an image of an object and processing the image based on an image processing operation to provide a processed image, where the image processing affects color of the object. The method further includes determining color adjustment parameters using a trained neural network, wherein an input to the trained neural network is based on the image and the processed image, restoring color in the processed image based on the color adjustment parameters to produce a color-restored image, and displaying the color-restored image on a display device.

A method for color restoration in images includes accessing an image of an object and processing the image based on an image processing operation to provide a processed image, where the image processing affects color of the object. The method further includes determining color adjustment parameters using a trained neural network, wherein an input to the trained neural network is based on the image and the processed image, restoring color in the processed image based on the color adjustment parameters to produce a color-restored image, and displaying the color-restored image on a display device.

An image processing device including: a gain value manager for generating white gain values corresponding to a plurality of positions, based on a sensing result of a predetermined white image; a target pixel manager for detecting saturated pixels, based on pixel values received from an external device, and determining target pixels as saturated white pixels of which each have a pixel value that indicates that the saturated white pixel is saturated, based on peripheral pixels of the saturated white pixels among the detected saturated pixels; and a target pixel corrector for changing pixel values of the target pixels, based on the white gain values and pixel values of the peripheral pixels.