Techniques for convolutional neural network-based multi-exposure fusion of multiple image frames and for deblurring multiple image frames

An electronic device comprising:

• at least one camera;
• and
• at least one processing device configured to:
• obtain multiple image frames of a scene using the at least one camera;
• use a convolutional neural network to generate blending maps associated with the image frames, wherein the blending maps contain or are based on both (i) a measure of motion in the image frames and (ii) a measure of how well exposed different portions of the image frames are;
• and
• generate a final image of the scene by blending at least some of the image frames based on at least some of the blending maps.

A non-transitory machine-readable medium containing instructions that when executed cause at least one processor of an electronic device to:

• obtain multiple image frames of a scene using at least one camera of the electronic device;
• use a convolutional neural network to generate blending maps associated with the image frames, wherein the blending maps contain or are based on both (i) a measure of motion in the image frames and (ii) a measure of how well exposed different portions of the image frames are;
• and
• generate a final image of the scene by combining at least some of the image frames based on at least some of the blending maps.