Abstract: A shadow brightening method includes receiving, at a memory device, an original input image, a brightening level, and a threshold pixel intensity. If a pixel intensity is greater than the threshold, then the pixel is considered bright. Otherwise, the pixel is shadowed. The method includes calculating a gamma transformation for each pixel. If the pixel intensity is less than or equal to the threshold, then a gamma transformation equal to the received brightening level is applied. If the pixel intensity is greater than the threshold, then the gamma transformation is scaled to decrease with intensity. For each shadowed pixel, the method includes computing a minimum value. It also includes determining the brightening level to be applied, thus creating a gamma map. The method also includes applying the determined brightening level to the shadowed pixels and outputting a shadow-brightened output image.

Abstract: Implementations of the disclosure are directed to predicting structured illumination parameters for a particular point in time, space, and/or temperature using estimates of structured illumination parameters obtained from structured illumination images captured by a structured illumination system. Particular implementations are directed to predicting structured illumination frequency, phase, orientation, and/or modulation order parameters.

Abstract: An image processing method transforms image sequences into luminances, filters the luminances, determines the temporal differences between the luminances, performs a frequency domain transformation on the temporal differences, and applies a temporal contrast sensitivity function envelope integral to the frequency transform output to generate a temporal image metric. The temporal image metric may be applied for example to train a neural network or to configure a display device to depict a visual indication of the temporal image metric.

Abstract: An image processing apparatus including a processor is provided. The processor inputs, from an imaging element in which first imaging pixels having a lower SNR and second imaging pixels having a higher SNR are arranged on a same layer, a first captured image by the first imaging pixels and a second captured image by the second imaging pixels when the first imaging pixels and the second imaging pixels perform imaging simultaneously, selects a target pixel from the first captured image, extracts, from the second captured image or an interpolated image of the second captured image, pixels having luminance values close to a luminance value of a pixel corresponding to the target pixel in the second captured image or interpolated image, selects pixels corresponding to the extracted pixels from the first captured image, and corrects a luminance value of the target pixel based on luminance values of the selected pixels.

Abstract: A video dehazing method includes: capturing a hazy image including multiple inputted pixels by an image capture module, calculating an atmospheric light value according to the inputted pixels by an atmospheric light estimation unit, determining a sky image area according to the inputted pixels via the intermediate calculation results of a guided filter by a sky detection unit; calculating a dark channel image according to the inputted pixels based on dark channel prior (DCP) by a dark channel prior unit; calculating a fine transmission image according to the inputted pixels, the atmospheric light value, the sky image area and the dark channel image via a guided filter by a transmission estimation unit, generating a dehazing image according to the inputted pixels, the atmospheric light value and the fine transmission image by an image dehazing unit, and outputting the dehazing image by a video outputting module.

Abstract: In some embodiments, an apparatus includes a memory and a processor operatively coupled to the memory. The processor is configured to receive an electronic document having a set of pages, and partition a page from the set of pages of the electronic document into a set of portions. The processor is configured to convert each portion of the set of portions into a negative image of a set of negative images. The processor is configured to produce, based on an artificial intelligence algorithm, a de-noised negative image of each negative image and convert each de-noised negative image of a set of de-noised negative images into a positive image of a set of positive images, and combine each positive image of the set of positive images to produce a de-noised page. The de-noised page has artifacts less than artifacts of the page of the electronic document.

Abstract: Embodiments of the present disclosure provide a CMOS image sensor, and a pixel circuit and a driving method thereof. The pixel circuit includes: a collection circuit configure to collect an incident light and convert a collected optical signal into an electric signal; a source follower circuit configured to output the received electric signal to a collection signal output terminal under the control of scan lines; and a voltage conversion circuit, configured to be connected to the collection signal output terminal through a read signal line, convert a voltage at the collection signal output terminal to an output voltage, and output the output voltage at a voltage output terminal, wherein the output voltage is within an operating voltage range of an image processor.

Abstract: A method and device for blending multiple related frames into a single frame to reduce noise is disclosed. A method includes comparing an input frame to a corresponding reference frame in order to determine if at least one object that is in both frames moves in the input frame, and also to determine edge strengths of the at least one object. The method further includes, based on the comparison, determining which regions of the input frame to blend with corresponding regions of the reference frame, which regions of the input frame not to blend with corresponding regions of the reference frame, and which regions of the input frame to partially blend with corresponding regions of the reference frame.

Abstract: An electronic apparatus includes a memory configured to store a predetermined conversion relation, and a processor configured to obtain first luminance information indicating luminance values of respective pixels included in a first image, and obtain first color information indicating color values of the respective pixels, obtain a first cumulative distribution function indicating a relation between a cumulative pixel count and each luminance level based on the first luminance information, obtain a second cumulative distribution function by applying the predetermined conversion relation to the first cumulative distribution function, calculate second luminance information indicating converted luminance values of the respective pixels by using the first cumulative distribution function and the second cumulative distribution function, and generate a second image based on the first color information and the second luminance information.

Abstract: Provided is an image processing apparatus that detects a predetermined image region of an object from a photographed image; generates a correction parameter; and corrects a high-luminance region by using a correction parameter, in which, in a case where the high-luminance region is in an image region having a predetermined image region of a plurality of objects overlapping with each other therein, to which object having the predetermined image region the high-luminance region belongs is judged, and, on the basis of information of the predetermined image region the high-luminance region belongs to, the correction parameter with which the high-luminance region in the overlapping image region is corrected is generated.

Abstract: Embodiments of the present disclosure disclose an image details processing method, comprises: obtaining each luminance data in the image; performing non-linear transformation on the each luminance data to obtain corresponding transformed data; performing the low frequency processing on the transformed data to obtain low frequency data; based on the low-frequency data and the transformed data, determining the corrected luminance data. The embodiments of the present disclosure also disclose an image details processing apparatus, a terminal, and a storage medium.

Abstract: A method for identifying skin region in an image includes: selecting a pixel in the target image; calculating a first probability of the pixel in a first color space, the first probability being a probability that the pixel represents skin in the first color space; calculating a second probability of the pixel in a second color space distinct from the first color space, the second probability being a probability that the pixel represents skin in the second color space; determining a combined probability that the pixel in the target image represents skin based on the first probability and the second probability; expanding the pixel into a skin region in the target image by repeating said steps of determining a combined probability that another pixel adjacent to the pixel represents skin until the skin region reaches a predefined size threshold; and performing a predefined beautifying process to the pixels.

Abstract: An apparatus and a method that decrease a banding phenomenon in a subsampled image and achieve high image quality are provided. A subsampled image obtained by copying an adjacent pixel value to a pixel value thinning position is accepted as an input image; a correction target signal global gain is calculated as a ratio between a slope of a correction target signal and a slope of a luminance signal of a global region made up of a plurality of consecutive pixels including a pixel position of the correction target pixel of the input image; a luminance local slope is calculated as a slope of the luminance signal of a local region which is a region within the global region, including the pixel position of the correction target pixel of the input image and smaller than the global region; and a corrected pixel value of the correction target pixel is calculated.

Abstract: Improved flight display systems and methods that selectively deemphasize terrain are provided. The method includes receiving and processing navigation reference point data, terrain data, and aircraft status data. Next, the method (a) renders on a display system, in real-time, a viewing segment defined as at least a navigation reference point for the aircraft, the viewing segment having terrain rendered in a first level of terrain contrast; and (b) determines that the aircraft is in a terrain deemphasis scenario when an altitude is certain low altitude operations. When the aircraft is in the terrain deemphasis scenario, the method deemphasizes terrain within a determined boundary in the viewing segment. Deemphasizing includes decreasing terrain contrast to a second level of terrain contrast within the boundary. Terrain contrast within the boundary is restored to the first level responsive to receiving a restore trigger.

Abstract: An image coding method includes: generating a predicted block; calculating a residual block; calculating quantized coefficients by performing transform and quantization on the residual block; calculating a coded residual block by performing inverse quantization and inverse transform on the quantized coefficients; generating a temporary coded block; determining whether or not an offset process is required, to generate first flag information indicating a result of the determination; executing the offset process on the temporary coded block when it is determined that the offset process is required; and performing variable-length coding on the quantized coefficients and the first flag information.

Abstract: At least one image processing apparatus, and at least one method, of the present invention(s) generate a corrected image obtained by removing, from a color image whose pixel values contain components derived from scattered light, at least part of the components derived from the scattered light. The at least one image processing apparatus includes a generation unit configured to generate the corrected image by correcting a pixel value of a first color component of each pixel in the color image by using a first reference intensity and a weight value, and by correcting a pixel value of a second color component of each pixel in the color image by using a second reference intensity and a weight value.

Abstract: Customer wide angle lenses and methods and apparatus for using such lenses in individual cameras as well as pairs of cameras intended for stereoscopic image capture are described. The lenses are used in combination with sensors to capture different portions of an environment at different resolutions. In some embodiments ground is capture at a lower resolution than sky which is captured at a lower resolution than a horizontal area of interest. Various asymmetries in lenses and/or lens and sensor placement are described which are particularly well suited for stereoscopic camera pairs where the proximity of one camera to the adjacent camera may interfere with the field of view of the cameras.

Abstract: In some examples, print quality diagnosis may include aligning corresponding characters between a scanned image of a printed physical medium aligned to a master image associated with generation of the printed physical medium to generate a common mask. Print quality diagnosis may further include determining, for each character of the scanned image, an average value associated with pixels within the common mask, and determining, for each corresponding character of the master image, the average value associated with pixels within the common mask. Further, print quality diagnosis may include determining, for each character of the common mask, a metric between the average values associated with the corresponding characters in the scanned and master images.

Abstract: Computer-implemented systems and methods herein disclose automatic haze correction in a digital video. In one example, a video dehazing module identifies a scene including a set of video frames. The video dehazing module identifies the dark channel, brightness, and atmospheric light characteristics in the scene. For each video frame in the scene, the video dehazing module determines a unique haze correction amount parameter by taking into account the dark channel, brightness, and atmospheric light characteristics. The video dehazing module applies the unique haze correction amount parameters to each video frame and thereby generates a sequence of dehazed video frames.

Abstract: To overcome several issues of autofocusing, a deep-learning-based autofocus system utilizes a subject's body to autofocus on the subject's face. The subject, including the subject's body and face/head, are determined utilizing image processing methods, and based on the detection, the subject's face/head is automatically focused on.

Abstract: A method of measuring lighting condition using dual cameras, having capturing a reference image, estimating a first minimum exposure target value, capturing a first plurality of minimum exposure value images, determining a first overall minimum exposure value, estimating a first maximum exposure target value, capturing a first plurality of maximum exposure value images, determining a first overall maximum exposure value of the first plurality of associated maximum exposure values and estimating a first dynamic exposure range as encompassing a first range having the first overall minimum exposure value as a first lower bound and the first overall maximum exposure value as a first upper bound.

Abstract: Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

Abstract: A method to process an image includes: determining a first specular reflection element from an input image based on a feature of chromaticity of pixels included in the input image; extracting a second specular reflection element from the first specular reflection element based on a feature of brightness of the pixels; and correcting the input image based on the second specular reflection element.

Abstract: An information handling system operating an adaptive HDR tone mapping system may comprise a display screen including a plurality of pixels operating at a lower dynamic range of brightness values, a graphics processor executing code instructions to prepare data of an HDR digital image for display at the lower dynamic range, to determine a relative brightness ratio comparing a number of pixels in the data for the image to display at a brightness level below a typical display brightness and at or above the typical display brightness, and to generate a tone map to modify the data of the image if the relative brightness ratio does not meet or exceed a preset threshold such that the pixels are mapped to a maximum brightness of a peaking display brightness level of the display screen, and the display screen displaying the plurality of pixels according to the first adaptive tone map modification.

Abstract: A method and a device for luminance adjustment, and a display device are provided. The luminance adjustment method includes: receiving an image data signal; and performing luminance adjustment on a dynamic image according to a target adjustment mode when a received image data signal belongs to the dynamic image, wherein the target adjustment mode is a luminance adjustment corresponding to a sum of luminance components in the image data signal among the plurality of adjustment modes; the plurality of adjustment modes includes a first mode, a second mode and a third mode, the range of luminance adjustment based on the second mode is between the one based on the first mode and the one based on the third mode. With the luminance adjustment method and device, the image flickering in displaying a dynamic image may be reduced.

Abstract: The present invention provides an image processing device and an image processing method capable of removing haze (reducing the effect of haze) without losing detail of a high-luminance subject. In the aspect of the present invention, the input image I is represented by I=J·t+A·(1?t) where an original image is J, an atmospheric light pixel value is A, and a transmittance is t. In this case, a dark channel value D of each pixel of the input image I is calculated, and is associated with the transmittance t having a value monotonically decreasing for each pixel of which D ranges from 0 to 1 and associated with the transmittance t having a value monotonically increasing for each pixel which corresponds to haze and of which D ranges from 1 to Dmax. In such a manner, the original image J is generated as a corrected image.

Abstract: An apparatus, system, and method of image processing, each of which: acquires a plurality of images respectively captured with a plurality of imaging elements, the plurality of images respectively corresponding to a plurality of frames of a video; calculates, for a current frame, an evaluation value to be used for evaluating each of the plurality of images using a pixel value of at least one pixel in an overlapping area of the plurality of images; determines whether an evaluation value of each of the plurality of images in a frame preceding the current frame is stored in a memory; determines at least one correction target image from the plurality of images based on the evaluation value calculated for the current frame and a determination result indicating whether the evaluation value in the preceding frame is stored; calculates a plurality of correction amounts to be used for correcting a plurality of evaluation values in the overlapping area of the correction target image, based on the evaluation value of th

Abstract: An image acquisition method operates in a hand held image acquisition device with a camera. A first image of a scene is obtained with the camera at a nominal exposure level. A number of relatively bright pixels and a number of relatively dark pixels within the first image are determined. Based on the number of relatively bright pixels, a negative exposure adjustment is determined and based on the number of relatively dark pixels, a positive exposure adjustment is determined. Respective images are acquired at the nominal exposure level; with the negative exposure adjustment; and with the positive exposure adjustment as component images for high dynamic range (HDR) image of the scene.

Abstract: Innovations in control and use of chroma quantization parameter (“QP”) values that depend on luma QP values. More generally, the innovations relate to control and use of QP values for a secondary color component that depend on QP values for a primary color component. For example, during encoding, an encoder determines a QP index from a primary component QP and secondary component QP offset. The encoder maps the QP index to a secondary component QP, which has an extended range. The encoder outputs at least part of a bitstream including the encoded content. A corresponding decoder receives at least part of a bitstream including encoded content. During decoding, the decoder determines a QP index from a primary component QP and secondary component QP offset, then maps the QP index to a secondary component QP, which has an extended range.

Abstract: A real-time video enhancement method performed at a terminal includes: obtaining an average luminance of a current frame of an image; in accordance with a determination that the average luminance is less than the luminance threshold: obtaining a pixel range of an area of interest of the current frame; determining a local enhancement curve of the current frame according to the pixel range of the area of interest of the current frame; determining a first enhancement curve corresponding to the current frame according to the average luminance of the current frame; determining a second enhancement curve of the current frame according to the local enhancement curve of the current frame and the first enhancement curve of the current frame; and adjusting the current frame according to the second enhancement curve.

Abstract: Provided is an electronic device including a display configured to display a first image; and one or more processors electrically connected with the display, wherein the one or more processors are configured to: select a region surrounding a first object comprising a first sub-region surrounding a first part of the first object and a second sub-region surrounding a second part of the first object from the first image, apply a first correction scheme to the first sub-region surrounding the first part of the first object, apply a second correction scheme to the second sub-region surrounding the second part of the first object, and generate a second image comprising the corrected first sub-region surrounding the first part of the first object and the corrected second sub-region surrounding the second part of the first object.

Abstract: Methods and apparatus for recording anonymized volumetric data from medical image visualization software are disclosed. An example method includes receiving a medical image; anonymizing the medical image outside of a region of interest by degrading the medical image outside a region corresponding to the region of interest and maintaining the resolution of the medical image inside the region corresponding to the region of interest; extracting data from the medical image; and generating an archive based on the anonymized medical image and the data.

Abstract: First representative pixel data is a maximum amount of light, when a light source is turned off. Second representative pixel data and third representative pixel data respectively represent a minimum amount of light and a maximum amount of light for a conspicuous channel to which a piece of data representing an amount of light smaller than an amount of light corresponding to a first threshold belongs. In an image reading device, a determination device, when the third representative pixel data represents an amount of light that is equal to or larger than an amount of light corresponding to at least a second threshold corresponding to the first representative pixel data, or a third threshold corresponding to the second representative pixel data and the first representative pixel data, determines that a device state is defective.

Abstract: Provided is an image processing apparatus which generates a wide dynamic range (WDR) image using an image sensor. The image processing apparatus includes: an image sensor which outputs image data having a plurality of image channels; a mode setting unit which changes a photographing mode from a first mode in which a first number of sub-images are synthesized to a second mode in which a second number of sub-images are synthesized, based on luminance of the output image data; a register setting unit which changes a register value of the image sensor according to the second mode; and an image signal processor (ISP) which generates a result image by synthesizing the second number of sub-images from the image data according to the changed register value, wherein the second number of sub-images have different exposure times.

Abstract: Exemplary methods, apparatuses, and systems for image processing are described. One or more reference images are selected based on image quality scores. At least a portion of each reference image is merged to create an output image. An output image with motion artifacts is compared to a target to correct the motion artifacts of the output image.

Abstract: An on-board diagnostic for a particle filter of a vehicle exhaust system records repeating data about flow and pressure around the particle filter. Data is recorded in virtual data bins having successive thresholds or filters within a numerical scale. Each data point is typically recorded in several bins to permit a rapid calculation of averaged data for use in the diagnostic. Sensitivity of less frequently recorded data is preserved, while giving quickly delivery of a result from the diagnostic.

Abstract: An imaging unit 20 has a configuration in which an identical polarization pixel block made up of a plurality of pixels with an identical polarization direction is provided for each of a plurality of polarization directions and pixels of respective predetermined colors are provided in the identical polarization pixel block. A correction processing unit 31 performs correction processing such as white balance correction on a polarized image generated by the imaging unit 20. A polarized image processing unit 32 separates or extracts a reflection component using the polarized image after the correction processing. By using a polarized image of the separated or extracted reflection component, for example, it is possible to generate normal line information with high accuracy.

Abstract: An image processor includes a curve generator and a gradation correcting unit. Based on a predetermined correspondence relationship between average luminance of an image and a gradation correction curve, the curve generator generates, in accordance with average luminance of an input image, a common curve, i.e. a gradation correction curve used to correct a gradation of the input image. The gradation correcting unit uses in common the common curve generated by the curve generator for red, green, and blue color signals of the input image to correct gradations of the red, green, and blue color signals. Based on first average luminance, i.e. an average value of luminance of a first region in the input image, second average luminance, i.e. an average value of luminance of a predetermined-colored second region included in the first region, and an area of the second region, the curve generator generates a common curve.

Abstract: A high-definition map system receives sensor data from vehicles travelling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date.

Abstract: Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

Abstract: Innovations in control and use of chroma quantization parameter (“QP”) values that depend on luma QP values. More generally, the innovations relate to control and use of QP values for a secondary color component that depend on QP values for a primary color component. For example, during encoding, an encoder determines a QP index from a primary component QP and secondary component QP offset. The encoder maps the QP index to a secondary component QP, which has an extended range. The encoder outputs at least part of a bitstream including the encoded content. A corresponding decoder receives at least part of a bitstream including encoded content. During decoding, the decoder determines a QP index from a primary component QP and secondary component QP offset, then maps the QP index to a secondary component QP, which has an extended range.

Abstract: Methods and systems for an image construction component capable of generating pixel information for certain regions of an image based on other, existing regions of the image. For example, the image construction component may identify a target block of pixels for which to generate pixel information and then use pixel information for pixels surrounding the target block of pixels in order to identify similar image information within pixels in another part of the image. These identified pixels may then be used in defining the pixel information of the target block of pixels and also used in blending the target block of pixels with the defined pixels surrounding the target block of pixels.

Abstract: A user terminal device and a method for controlling the same are provided. The user terminal device includes a sensor configured to sense a user touch operation for a binarized text image, a controller configured to generate an indicator pointing out a point where the user touch operation is sensed, when the user touch operation is sensed by the sensor, and a display unit configured to display the binarized text image and the generated indicator.

Abstract: An image correction apparatus generates a reduced smoothed image by smoothing a reduced image created from an input image; detects at least one edge pixel on the reduced image or the reduced smoothed image; calculates, for each pixel of the reduced image, a reflectance component of an object; calculates a correction factor having a value based on a reflectance component in accordance with a distribution of reflectance components other than the reflectance component of the edge pixel; generates an enlarged smoothed image by enlarging the reduced smoothed image; and generates a corrected image by calculating a luminance value of each pixel of the corrected image based on the correction factor and the reflectance component based on a ratio of a luminance value of a corresponding pixel of the input image to a luminance value of a corresponding pixel of the enlarged smoothed image.

Abstract: An image reading apparatus includes a line sensor configured to read an image of a target object. The line sensor includes light receiving element arrays arranged at given intervals in a second direction perpendicular to a first direction for a plurality of lines, the plurality of light receiving element arrays each including a first light receiving element configured to receive light of a first color and a second light receiving element configured to receive light of a second color different from the first color, which are arranged in the first direction to form one line. The image reading apparatus is configured to derive a shading correction coefficient for shading correction based on output from the light receiving element arrays that have read a reference white plate, and to identify, as an abnormal pixel, a pixel obtained by reading a foreign matter existing on the reference white plate.

Abstract: In a portable radio transceiver, a power amplifier system includes a saturation detector that detects power amplifier saturation in response to duty cycle of the amplifier transistor collector voltage waveform. The saturation detection output signal can be used by a power control circuit to back off or reduce the amplification level of the power amplifier to avoid power amplifier control loop saturation.

Abstract: The present invention relates to a method, system and non-transitory computer-readable recording medium for measuring ball spin. According to one aspect of the invention, there is provided a method for measuring ball spin, comprising the steps of: detecting at least one mark appearing in a region corresponding to a ball in each of a plurality of images in which the ball is photographed, wherein a physical quantity of the ball is to be measured; recognizing a mark commonly detected over a first image and a second image that are temporally adjacent, with reference to information on properties of the at least one detected mark in each of the plurality of images, and generating a mark sequence including information on the properties of the recognized mark in the first and second images; and measuring a physical quantity related to spin of the ball with reference to the generated mark sequence.

Abstract: By either subsampling neighbor pixels and deriving an illumination variation parameter, or deriving one normalization shift value of two normalization shift values for normalizing parameters which are used when deriving the illumination variation parameter, with a dependency on the other normalization shift value, an amount of calculation for illumination compensation is reduced.

Abstract: Customer wide angle lenses and methods and apparatus for using such lenses in individual cameras as well as pairs of cameras intended for stereoscopic image capture are described. The lenses are used in combination with sensors to capture different portions of an environment at different resolutions. In some embodiments ground is capture at a lower resolution than sky which is captured at a lower resolution than a horizontal area of interest. Various asymmetries in lenses and/or lens and sensor placement are described which are particularly well suited for stereoscopic camera pairs where the proximity of one camera to the adjacent camera may interfere with the field of view of the cameras.

Abstract: This invention provides methods for spatially localized image editing. For example, an input image is divided into multiple bins in each dimension. For each bin, a histogram is computed, along with local image statistics such as mean, medium and cumulative histogram. Next, for each tile, a type of adjustment is determined and applied, including adjustment associated with Exposure, Brightness, Shadows, Highlights, Contrast, and Blackpoint. The adjustments are done for all tiles in the input image to render a small adjustment image. The small image is then interpolated, for example, using an edge-preserving interpolation, to get a full size adjustment image with adjustment curve for each pixel. Subsequently, per-pixel image adjustments can be performed across an entire input image to render a final adjusted image.