A distance measurement accuracy is improved without increasing power consumption of an image processing apparatus that performs distance-measuring processing. In one embodiment, an image processing apparatus for calculating distance information on an image has a reliability calculation unit 113 configured to calculate reliability in accordance with contrast for each pixel of the image and a distance calculation unit 116 configured to calculate distance information on each of the pixels based on reliability of each of the pixels. The distance calculation unit 116 calculates the distance information about a second pixel group whose reliability is lower than that of a first pixel group by using a collation area whose size is larger than a predetermined size in a range in which an amount of calculation in a case where a collation area of the predetermined size is used for all the pixels of the image is not exceeded.

A distance measurement accuracy is improved without increasing power consumption of an image processing apparatus that performs distance-measuring processing. In one embodiment, an image processing apparatus for calculating distance information on an image has a reliability calculation unit 113 configured to calculate reliability in accordance with contrast for each pixel of the image and a distance calculation unit 116 configured to calculate distance information on each of the pixels based on reliability of each of the pixels. The distance calculation unit 116 calculates the distance information about a second pixel group whose reliability is lower than that of a first pixel group by using a collation area whose size is larger than a predetermined size in a range in which an amount of calculation in a case where a collation area of the predetermined size is used for all the pixels of the image is not exceeded.

Systems and methods for hybrid depth regularization in accordance with various embodiments of the invention are disclosed. In one embodiment of the invention, a depth sensing system comprises a plurality of cameras; a processor; and a memory containing an image processing application. The image processing application may direct the processor to obtain image data for a plurality of images from multiple viewpoints, the image data comprising a reference image and at least one alternate view image; generate a raw depth map using a first depth estimation process, and a confidence map; and generate a regularized depth map. The regularized depth map may be generated by computing a secondary depth map using a second different depth estimation process; and computing a composite depth map by selecting depth estimates from the raw depth map and the secondary depth map based on the confidence map.

Systems and methods for hybrid depth regularization in accordance with various embodiments of the invention are disclosed. In one embodiment of the invention, a depth sensing system comprises a plurality of cameras; a processor; and a memory containing an image processing application. The image processing application may direct the processor to obtain image data for a plurality of images from multiple viewpoints, the image data comprising a reference image and at least one alternate view image; generate a raw depth map using a first depth estimation process, and a confidence map; and generate a regularized depth map. The regularized depth map may be generated by computing a secondary depth map using a second different depth estimation process; and computing a composite depth map by selecting depth estimates from the raw depth map and the secondary depth map based on the confidence map.

A system and method for image processing are provided. A pre-processed image may be obtained. The pre-processed image may be decomposed into a low-frequency image and a high-frequency image. At least one grayscale transformation range may be determined based on the low-frequency image. At least one grayscale transformation parameter may be determined based on the at least one grayscale transformation range. The low-frequency image may be transformed based on the at least one grayscale transformation parameter to obtain a transformed low-frequency image. A transformed image may be generated by reconstructing the transformed low-frequency image and the high-frequency image.

A system and method for image processing are provided. A pre-processed image may be obtained. The pre-processed image may be decomposed into a low-frequency image and a high-frequency image. At least one grayscale transformation range may be determined based on the low-frequency image. At least one grayscale transformation parameter may be determined based on the at least one grayscale transformation range. The low-frequency image may be transformed based on the at least one grayscale transformation parameter to obtain a transformed low-frequency image. A transformed image may be generated by reconstructing the transformed low-frequency image and the high-frequency image.

Provided is an apparatus for acquiring images including an image sensor including a sensor substrate including a plurality of photo-sensing cells sensing light, and a color separation lens array provided above the sensor substrate, the color separation lens array including a fine structure in each of a plurality of regions respectively facing the plurality of photo-sensing cells and separating incident light based on color, the fine structure forming a phase distribution to condense light having different wavelengths on adjacent photo-sensing cells, a signal processor configured to perform, based on a point spread function corresponding to each color pixel by the color separation lens array, deconvolution on sensing signals of the plurality of photo-sensing cells to process an image signal for each color obtained by the image sensor, and an image processor configured to form a color image from the image signal for each color processed by the signal processor.

Provided is an apparatus for acquiring images including an image sensor including a sensor substrate including a plurality of photo-sensing cells sensing light, and a color separation lens array provided above the sensor substrate, the color separation lens array including a fine structure in each of a plurality of regions respectively facing the plurality of photo-sensing cells and separating incident light based on color, the fine structure forming a phase distribution to condense light having different wavelengths on adjacent photo-sensing cells, a signal processor configured to perform, based on a point spread function corresponding to each color pixel by the color separation lens array, deconvolution on sensing signals of the plurality of photo-sensing cells to process an image signal for each color obtained by the image sensor, and an image processor configured to form a color image from the image signal for each color processed by the signal processor.

A method includes generating first contrast significance data for a first computer vision model generated from a first training set of medical scans. First significant contrast parameters are identified based on the first contrast significance data. A first re-contrasted training set is generated based on performing a first intensity transformation function on the first training set of medical scans, where the first intensity transformation function utilizes the first significant contrast parameters. A first re-trained model is generated from the first re-contrasted training set, which is associated with corresponding output labels based on abnormality data for the first training set of medical scans. Re-contrasted image data of a new medical scan is generated based on performing the first intensity transformation function. Inference data indicating at least one abnormality detected in the new medical scan is generated based on utilizing the first re-trained model on the re-contrasted image data.

A method includes generating first contrast significance data for a first computer vision model generated from a first training set of medical scans. First significant contrast parameters are identified based on the first contrast significance data. A first re-contrasted training set is generated based on performing a first intensity transformation function on the first training set of medical scans, where the first intensity transformation function utilizes the first significant contrast parameters. A first re-trained model is generated from the first re-contrasted training set, which is associated with corresponding output labels based on abnormality data for the first training set of medical scans. Re-contrasted image data of a new medical scan is generated based on performing the first intensity transformation function. Inference data indicating at least one abnormality detected in the new medical scan is generated based on utilizing the first re-trained model on the re-contrasted image data.