An image capturing apparatus includes an image sensor configured to change an exposure condition for each of a plurality of exposure areas, each of the exposure areas including a single pixel or a plurality of pixels, and an image processing unit configured to perform steps of digital signal processing on a signal of a captured image includes generating a plurality of coupled areas in which the exposure areas are coupled based on a first threshold of the exposure condition, calculating a development parameter for each of the coupled areas, and applying the development parameter to the image processing unit for each of the exposure areas.

Disclosed is a method for producing metadata, comprising: acquiring a first image and a second image which have different gamuts; acquiring at least one of white point information and gamut information with respect to the second image; correcting the first image on the basis of the acquired information; and producing metadata on the basis of the correspondence relationship of color information between the corrected first image and the second image.

A disclosed scaler resource includes a color management module configured to support two or more color space transformations and two or more color temperature adjustment profiles and to receive first pixel data and perform color processing of the first pixel data to produce second pixel data. The color processing includes a color space transformation in accordance with any of the supported color space transformation matrices and a color temperature adjustment in accordance with any of the supported color temperature adjustment profiles. The color processing is configured wherein a ratio of primary colors produced by performing the color processing on first pixel data corresponding to any primary color is independent of the selected color temperature adjustment profile. The color space transformation may be performed before or after the color temperature adjustment. When performed before, the color transformation matrix is modified to reflect the color temperature adjust profile.

Introduced here are computer programs and associated computer-implemented techniques for achieving high-fidelity color reproduction in the absence of any known reflectance spectrums. That is, high-fidelity color reproduction can be achieved without portable references, such as gray cards and color checkers. To accomplish this, a new reference spectrum—the “reference illuminant spectrum”—is introduced into scenes to be imaged by image sensors. The reference illuminant spectrum is created by a multi-channel light source whose spectral properties are known.

Methods and systems for the display management of HDR video signals are presented. The mapping is based on tone mapping and color volume mapping which map an input signal with an input dynamic range and color volume to a target display with a target dynamic range and color volume. Both a global tone-mapping and precision-mapping methods using pyramid filtering are presented.

A contrastive learning method for color constancy employs a fully-supervised construction of contrastive pairs, driven by a novel data augmentation. The contrastive learning method includes receiving two training images, constructing positive and negative contrastive pairs by the novel data augmentation, extracting representations by a feature extraction function, and training a color constancy model by contrastive learning representations in the positive contrastive pair are closer than representations in the negative contrastive pair. The positive contrastive pair contains images having an identical illuminant while negative contrastive pair contains images having different illuminants. The contrastive learning method improves the performance without additional computational costs. The desired contrastive pairs allow the color constancy model to learn better illuminant feature that are particular robust to worse-cases in data sparse regions.

Methods and systems are provided for generating a virtual view of a scene associated with a vehicle. In one embodiment, a method includes: obtaining image data including a plurality of images captured by a plurality of cameras of the vehicle; obtaining steering angle data captured by a sensor of the vehicle; detecting, by a processor, a shadow in at least one image of the plurality of images; determining, by the processor, auto-white balance data for each image of the plurality of images; selectively combining, by the processor, the auto-white balance data of the images based on the detected shadow, and the steering angle data; and generating, by the processor, output image data based on the combined auto-white balance data and the image data.

The present disclosure discloses a multicolor barcode. The multicolor barcode includes a start region (1), a data region (2), and a check region (3). The start region (1), the data region (2), and the check region (3) are arranged in sequence. The start region (1) includes a start color block that indicates a start position of the multicolor barcode, the data region (2) includes a data color block that indicates encoded data of the multicolor barcode, and the check region (3) includes a check color block that indicates an end position of the multicolor barcode. The start color block includes a first color block and a second color block, the first color block is located at the start position, and the second color block is a white color block. The present disclosure further provides a color calibration method for a multicolor barcode, and a computer-readable storage medium.

A device and a method for generating an output image in which a subject has been captured are provided. A method of performing image processing may include: obtaining a raw image by a camera sensor of the device, by using a first processor configured to control the device; inputting the raw image to a first artificial intelligence (AI) model trained to scale image brightness, by using a second processor configured to perform AI-based image processing on the raw image; obtaining tone map data output from the first AI model, by using the second processor; and storing an output image generated based on the tone map data.

An image capturing apparatus that can obtain an optimum image in accordance with a region of interest of a user is provided. An image processing apparatus comprises an image synthesis unit configured to synthesize a visible light image and an infrared light image and generate a synthesis image; a region specifying unit configured to specify a region in the synthesis image; and an evaluation unit configured to evaluate the saturation of the synthesis image in a region specified by the region specifying unit. The image synthesis unit changes the synthesis ratio of the visible light image and the infrared light image in the synthesis image in accordance with the saturation that has been evaluated by the evaluation unit.