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.

Abstract: Disclosed is method of image processing for three-dimensional reconstruction in an extended reality environment. The method includes defining a set of visual-attributes derived from reference images; identifying presence of at least one visual-attribute in a displayable content of target images to be used for the three-dimensional reconstruction; and modifying the displayable content of the target images, by concealing or displaying the identified at least one visual-attribute, for the three-dimensional reconstruction in the extended reality environment.

Abstract: Disclosed is a display apparatus including at least one speaker per ear; at least one sensor; and at least one processor coupled to the at least one speaker and the at least one sensor. The at least one processor is configured to receive, from the at least one sensor, sensor data indicative of a usage context of the display apparatus; process at least the received sensor data to determine the usage context; and adjust a value of at least one audio parameter for the at least one speaker, based on the determined usage context.

Abstract: Disclosed is a video streaming system with server(s) and client device(s) that are communicably coupled. The server(s) is configured to: receive HDR video content comprising HDR images; analyse dynamic range and colour characteristics; receive, from client device(s), first metadata indicative of viewing conditions of HDR video content; adjust HDR mastering parameters, based on first metadata and analysis; perform HDR mastering and compress HDR images; send to client device, compressed HDR images and second metadata indicative of adjusted HDR mastering parameters. The client device(s) is configured to receive compressed HDR images and second metadata; decompress compressed HDR images; translate pixel values in decompressed images based on second metadata; receive real-world images from camera(s); compose XR images using decompressed HDR images and real-world images; send to server, first metadata for next HDR video content; and display XR images on display(s) of client device.