Device and method for exposure correction using a low-resolution brightness map

A method for exposure correction, the method comprising:

• 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;
• wherein the step of guiding the at least one image based on the low-resolution brightness map is performed using at least one neural network, wherein an input of the at least one neural network comprises the at least one image and the low-resolution brightness map, and an output of the at least one neural network comprises at least one corrected image having at least one correctly-illuminated area, and wherein the at least one neural network is continuously trained to identify and correct the at least one inaccurately-illuminated area of the at least one image.

A head-mounted display device comprising:

• at least one camera for capturing at least one image;
• and
• a processor operatively coupled to the at least one camera, wherein the processor is configured to:
• receive the at least one image;
• define 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
• correct 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;
• wherein the low-resolution brightness map is defined as a matrix of target brightness values, one for each pixel in the at least one image, and wherein the processor is further configured to determine a given target brightness value corresponding to each pixel as one of:
• an average-brightness value that is determined using the brightness values of all pixels in any one of:
• the at least one image, at least one previously-captured image,
• a brightness value that is determined based on an exposure level corresponding to each pixel in any one of:
• the at least one image, at least one previously-captured image.

A head-mounted display device comprising:

• at least one camera for capturing at least one image;
• and
• a processor operatively coupled to the at least one camera, wherein the processor is configured to:
• receive the at least one image;
• define 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
• correct 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;
• wherein when fusing the at least one image and the low-resolution brightness map, the processor is configured to use at least one neural network, wherein an input of the at least one neural network comprises the at least one image and the low-resolution brightness map, and an output of the at least one neural network comprises at least one corrected image having at least one correctly-illuminated area, and wherein the at least one neural network is continuously trained to identify and correct the at least one inaccurately-illuminated area of the at least one image.