Scene motion correction in fused image systems

A non-transitory program storage device comprising instructions stored thereon, the instructions readable by one or more processors and configured to cause one or more processors to:

• obtain one or more first images of a scene, wherein each first image has a first exposure time;
• store the one or more first images in a memory;
• obtain one or more second images of the scene, wherein each second image has a second exposure time shorter than the first exposure time;
• store the one or more second images in the memory;
• determine a weight mask based, at least in part, on the one or more first images and the one or more second images, wherein the weight mask defines a relative contribution of each of the one or more first images and the one or more second images for a given region of a fused output image;
• fuse the first and second images based, at least in part, on the weight mask to generate an output image, the output image comprising a plurality of regions;
• and
• denoise each region of the output image, wherein each region of the output image is denoised based on the relative contributions of the one or more first images and the one or more second images to the respective region.

A method, comprising:

• obtaining one or more first images of a scene, wherein each first image has a first exposure time;
• storing the one or more first images in a memory;
• obtaining one or more second images of the scene, wherein each second image has a second exposure time shorter than the first exposure time;
• storing the one or more second images in the memory;
• determining a weight mask based, at least in part, on the one or more first images and the one or more second images, wherein the weight mask defines a relative contribution of each of the one or more first images and the one or more second images for a given region of a fused output image;
• fusing the first and second images based, at least in part, on the weight mask to generate an output image, the output image comprising a plurality of regions;
• and
• denoising each region of the output image, wherein each region of the output image is denoised based on the relative contributions of the one or more first images and the one or more second images to the respective region.