Abstract: Disclosed is an imaging system with image sensor and processor(s). The image sensor has a plurality of photo-sensitive cells and a colour filter array. The processor(s) is configured to read out unprocessed colour data from those photo-sensitive cells that correspond to the colour filters of the at least three different colours; generate coarse depth data by processing data read out from at least one of: those photo-sensitive cells that correspond to the colour filters that allow the at least one infrared wavelength to pass through the PDAF photo-sensitive cells; perform interpolation and demosaicking on the unprocessed colour data and the coarse depth data, using at least one neural network, to generate a full-resolution colour data and a full-resolution depth data; and reproject the full-resolution colour data from a given camera pose to a given eye pose of a user, by utilising the full-resolution depth data.

Abstract: A display apparatus including a display module with a display; and a gaze-tracking system with a plurality of light emitters and at least one light sensor, wherein the plurality of light emitters are arranged within a predefined region of an active area of the display module.

Abstract: An image sensor with photo-sensitive cells arranged on a photo-sensitive surface; and a colour filter array having smallest repeating units, wherein: a given smallest repeating unit has at least a first sub-unit and a second sub-unit. Image data is read out from the image sensor, wherein when reading out, processor(s) is/are configured to: selectively read out the image data from those photo-sensitive cells in a first region that correspond to respective first sub-units of smallest repeating units in the first region; and selectively skip reading out from those photo-sensitive cells in a second region that correspond to respective first sub-units of at least a first predefined percent of smallest repeating units in the second region; and process the image data to generate image(s).

Abstract: A method for deblurring distortion-corrected images, includes: obtaining a video-see-through (VST) image of a real-world environment; determining a given region of the VST image, based on at least one of: a distortion profile of a camera lens of at least one VST camera, blur characteristics of the camera lens, a scaling ratio between a resolution of the at least one VST camera and a resolution of a display whereat the VST image is to be displayed; and performing an undistortion deblurring operation on the given region of the VST image, by utilising at least one of: (i) a deblurring deconvolution filter, (ii) at least one neural network, based on locations of pixels of the given region, to generate an output image.

Abstract: Disclosed is an imaging system with an image sensor and processor(s). The image sensor has a plurality of photo-sensitive cells arranged on a photo-sensitive surface of the image sensor; a colour filter array with colour filters of at least three different colours; and a polarisation mask with polarisation filters arranged on an optical path of at most a first predefined percent of the colour filters. The processor(s) is/are configured to: read out image data from the image sensor; and process the image data to generate at least one of: a full-resolution colour image, a full-resolution polarisation image, a high-dynamic range (HDR) image.

Abstract: An optical arrangement for reducing reflections in camera includes image sensor with a light-sensitive surface and a filter arranged at a first distance from the light sensitive surface along an optical axis of optical arrangement. The filter includes a first curved surface facing a light-sensitive surface, and a second surface opposite to the first curved surface. The light-sensitive surface is configured to receive light and reflect received light towards the filter. The filter is configured to reflect light between a first curved surface and a second surface inside the filter. Reflections between the filter and the light sensitive surface are reduced.

Abstract: Image data from an image sensor is read out, wherein when reading out, processor(s) is/are configured to employ subsampling. The image data is processed, using neural network(s), to generate an image.

Abstract: A method includes detecting when a prescription lens is attached to a display apparatus; obtaining metadata associated with the prescription lens, upon the detection; determining whether the prescription lens belongs to a given set of prescription lenses that are pre-known to be compatible with the display apparatus, based on the obtained metadata; when it is determined that the prescription lens belongs to the given set of prescription lenses, obtaining at least one compensatory parameter corresponding to the prescription lens from a first data repository; and implementing prescription lens compensation by employing the at least one compensatory parameter, wherein the prescription lens compensation includes one or more of: processing at least one of: gaze-tracking data, extended-reality images to be displayed by the display apparatus, adjusting at least one physical setting of the display apparatus.

Abstract: Disclosed is a display apparatus with at least one display or projector; a gaze-tracking means; and at least one processor configured to process gaze-tracking data, collected by the gaze-tracking means, to determine a gaze direction of a user; identify a gaze region and a peripheral region within an image that is to be displayed by the at least one display or projector, based on the gaze direction; apply at least one image restoration technique on the image in an iterative manner such that M iterations of the at least one image restoration technique are applied on the gaze region, and N iterations of the at least one image restoration technique are applied on the peripheral region, M being different from N; and control the at least one display or projector to display the image having the at least one image restoration technique applied thereon.

Abstract: Disclosed is a method for enabling exposure-guided three-dimensional (3D) reconstruction, including (i) receiving Low Dynamic Range (LDR) input image captured by camera; (ii) rendering High Dynamic Range (HDR) image corresponding to input image, using HDR 3D reconstruction model pre-trained for HDR image reconstruction of 3D environment; (iii) applying HDR to LDR tone-mapping operator on HDR image, for producing tone-mapped LDR image; (iv) determining first loss function (FLF) between input image and tone-mapped LDR image, FLF comprising weighted pixel value differences between pixels of input image and corresponding pixels of tone-mapped LDR image; (v) determining whether input image has saturated pixel(s), saturated pixel(s) comprises: highlight saturated pixel, shadow saturated pixel; (vi) de-weighting pixel value difference corresponding to saturated pixel in FLF; (vii) back-propagating gradient of FLF with respect to model parameters, through differentiable render function of HDR 3D reconstruction model,

Abstract: Disclosed is a method that includes detecting a beginning of a movement of a user's gaze by processing gaze-tracking data, collected by a gaze-tracking means; predicting a motion blur in an image which is to be captured by at least one camera during the movement of the user's gaze, using a portion of the gaze-tracking data that corresponds to the beginning of the movement of the user's gaze; and compensating for the predicted motion blur while capturing the image by controlling the at least one camera.

Abstract: Image data from an image sensor (102, 202, 302, 402) is read out, wherein when reading out, processor(s) (104, 204, 304, 404) is/are configured to employ subsampling. The image data is processed, using neural network(s), to generate an image.

Abstract: A method including: obtaining images captured using camera(s), depth maps corresponding to images, and pose information; identifying image segment(s) for first image and second image; determining first relative pose of same object captured in first image; determining second relative pose of same object captured in second image; when same object is in-focus in first image, reprojecting at least image segment(s) of first image; and determining for given camera that captured second image a point spread function as function of optical depth; obtaining third image captured using given camera and third depth map corresponding to third image; and applying extended depth-of-field correction to image segment(s) of third image that is out of focus, by using point spread function.

Abstract: An imaging system has an image sensor chip and processor(s). The image sensor chip has a photo-sensitive surface with photo-sensitive cells; a colour filter array with physical smallest repeating units, wherein a given physical smallest repeating unit has array(s) of a first type of colour filters, array(s) of a second type of colour filters, and array(s) of a third type of colour filters; and a controller configured to employ neural network(s) during read out of image data. The processor(s) is/are configured to: receive output image data, wherein a smallest repeating unit in a colour pattern of at least a part of the output image data is different from the given physical smallest repeating unit; and generate an output image.

Abstract: An imaging system includes an image sensor, a wobulator employed to perform sub-pixel shifts; and processor(s) configured to: obtain, in a cycle, two or three sub-images from the image sensor; control the wobulator to perform, during said cycle, one or two sub-pixel shifts, wherein step sizes of sub-pixel shifts vary within at least one of: same cycle, different cycles, wherein at least one of step sizes is X pixel, wherein X is a fraction lying between 0 and 1, at least one other of step sizes is Y pixels, wherein Y is an integer lying in a range from 1 to Z, Z being equal to a number of pixels of same colour lying along a direction of sub-pixel shift in a smallest repeating M×N array (204a-b) in the image sensor; and process the two or three sub-images to generate image(s).

Abstract: Disclosed is system (100) comprising at least one server (102) configured to: obtain at least two images of real-world environment whose fields of view overlap at least partially; obtain pose information indicative of corresponding camera poses from which at least two images are captured; detect, in at least two images, at least one object (202A-202G) that is in contact with given plane (204, 208) present in real-world environment; identify, in at least two images, same features (206A-206J) of at least one object that lie on given plane; determine poses of same features, wherein pose of given same feature is determined, based on disparity in two-dimensional positions of given same feature in at least two images and corresponding camera poses from which at least two images are captured; and estimate given plane based on poses of same features.

Abstract: A method incorporating spatially-defined video-see-through (VST) modifications. includes receiving VST images (300a-c) of a real-world environment captured using at least one VST camera (208a-b) and depth data corresponding to the VST images; receiving a pose of at least one object present in the environment; analysing the VST images, depth data, and pose of the object(s), for identifying in a given VST image, change(s) in at least one spatial volume surrounding the object(s); determining a range of optical depth values for each pixel of the given VST image, by projecting the spatial volume(s) onto image coordinates; determining whether an optical depth value of a pixel of the given VST image lies within the range of optical depth values determined for the pixel; and applying image processing operation(s) on the pixel, when said determination is true.

Abstract: Disclosed is method for exposure correction. The method includes receiving at least one image; defining a low-resolution brightness map, associated with the at least one image, corresponding to an ambient lighting condition in which the at least one image is captured; and correcting an exposure in the at least one image, to restore at least one inaccurately-illuminated area of the at least one image, by guiding the at least one image based on the low-resolution brightness map, wherein the at least one inaccurately-illuminated area is at least one of: at least one under-illuminated area of the at least one image, at least one over-illuminated area of the at least one image.

Abstract: Disclosed is a system with server(s) configured to: obtain a plurality of input images captured by a plurality of input cameras comprising at least a first input camera per eye and a second input camera per eye, wherein a first field of view of the first input camera is narrower than a second field of view of the second input camera and is overlapping with an overlapping portion of the second field of view, the plurality of input images comprising at least a first input image and a second input image captured by the first input camera and the second input camera, respectively; and process the plurality of input images, by using neural style transfer network(s), to generate a single output image per eye.

Abstract: A system with at least one server configured to: obtain a plurality of input images captured by a plurality of input cameras comprising at least a first input camera per eye and a second input camera per eye, where a first field of view of the first input camera is narrower than a second field of view of the second input camera and is overlapping with an overlapping portion of the second field of view, the plurality of input images comprising at least a first input image and a second input image captured by the first input camera and the second input camera, respectively; and process the plurality of input images by using at least one neural style transfer network to generate a single output image per eye.