Abstract: A system and method are provided for generating colorized image data for a single-channel image using a ML network, as well as a system and method for training the ML network. The image colorization method includes: obtaining single-channel image data representing a single-channel image; generating image feature data as a result of inputting the single-channel image data into an encoder; generating a pixel decoder output through inputting the image feature data into a pixel decoder; generating a color decoder output through inputting the image feature data into a color decoder; and generating colorized image data based on the color decoder output and the pixel decoder output, wherein the colorized image data represents a colorized version of the single-channel image.

Abstract: A visual display output retargeting system and method, and visual display output control system having the visual display output retargeting system and implementing the method. The method includes: determining target driver attention data for a vehicle operator, wherein the target driver attention data indicates one or more target regions of a visual display output to be displayed to the vehicle operator; and determining visual display output data representing the visual display output as adjusted based on the target driver attention data for the vehicle operator through making adjustments to content of one or more retargeted regions of the visual display output so as to increase or decrease a likelihood of drawing the visual attention of the vehicle operator towards said retargeted region(s).

Abstract: An in-vehicle display immersive system and method is provided, particularly for generating a visual output for a vehicle cabin. The method includes: determining a color tone profile, a texture style profile and/or a driver emotion profile, wherein the color tone profile and/or the texture style profile are determined based on image data captured by an exteriorly-facing camera, and wherein the driver emotion profile is determined based on sensor data captured by a driver monitoring sensor; and determining a visual output based on the driver emotion profile, the color tone profile, and/or the texture style profile.

Abstract: Herein, there are provided backlight extraction techniques used for local dimming displays, including techniques for training a backlight extraction model and controlling a local dimming display based on backlight extraction values generated by a trained backlight extraction model. The backlight extraction model is characterizable by its use of separate power regularizations for different local dimming regions, particularly where the local dimming regions are each defined, for a given image to be displayed, as the areas of the given image corresponding to luminance characteristics being below or above a threshold amount for the given image. According to aspects herein, the threshold amount for the given image is determined based on projected backlight extraction values so as to obtain a dark local dimming region and a bright local dimming region, each of which has a different power regularization value applied thereto during a process for controlling backlights of the local dimming display.

Abstract: A visual display output retargeting system and method, and visual display output control system having the visual display output retargeting system and implementing the method. The method includes: determining target driver attention data for a vehicle operator, wherein the target driver attention data indicates one or more target regions of a visual display output to be displayed to the vehicle operator; and determining visual display output data representing the visual display output as adjusted based on the target driver attention data for the vehicle operator through making adjustments to content of one or more retargeted regions of the visual display output so as to increase or decrease a likelihood of drawing the visual attention of the vehicle operator towards said retargeted region(s).

Abstract: A system and method are provided for enhancing content to be displayed on a transparent display. This content enhancement method for a transparent display includes: obtaining content to be displayed on a transparent display; obtaining ambient light data from an ambient light sensor; obtaining transparent display background data for the transparent display; determining localized visibility degradation data for a plurality of local portions of the transparent display, wherein the localized visibility degradation is determined based on the ambient light data and the transparent display background data; and generating enhanced content for display on the transparent display based on the localized visibility degradation data.

Abstract: A system and method are provided for generating colorized image data for a single-channel image using a ML network, as well as a system and method for training the ML network. The image colorization method includes: obtaining single-channel image data representing a single-channel image; generating image feature data as a result of inputting the single-channel image data into an encoder; generating a pixel decoder output through inputting the image feature data into a pixel decoder; generating a color decoder output through inputting the image feature data into a color decoder; and generating colorized image data based on the color decoder output and the pixel decoder output, wherein the colorized image data represents a colorized version of the single-channel image.

Abstract: A system and method are provided for estimating a depth of an object within an image and training a depth estimation network. The depth estimation method includes: obtaining single-frame image data; obtaining scaling factor data based on the single-frame image data; generating scale-invariant depth data through inputting the single-frame image data into a depth estimation network; and generating metric depth data based on the scaling factor data and the scale-invariant depth data. The training method includes: inputting image data into a teacher machine learning (ML) model in order to generate metric depth data; inputting image data into a student ML model in order to generate scale-invariant depth data; and training a student network based on loss calculated using the metric depth data and the scale-invariant depth data.

Abstract: An in-vehicle display immersive system and method is provided, particularly for generating a visual output for a vehicle cabin. The method includes: determining a color tone profile, a texture style profile and/or a driver emotion profile, wherein the color tone profile and/or the texture style profile are determined based on image data captured by an exteriorly-facing camera, and wherein the driver emotion profile is determined based on sensor data captured by a driver monitoring sensor; and determining a visual output based on the driver emotion profile, the color tone profile, and/or the texture style profile.